Skip to content

aiskillstore/marketplace / skills/abdullahmalik17/context7-efficient

context7-efficient

Verified

Token-efficient library documentation fetcher using Context7 MCP with 86.8% token savings through intelligent shell pipeline filtering. Fetches code examples, API references, and best practices for JavaScript, Python, Go, Rust, and other libraries. Use when users ask about library documentation, need code examples, want API usage patterns, are learning a new framework, need syntax reference, or troubleshooting with library-specific information. Triggers include questions like "Show me React hooks", "How do I use Prisma", "What's the Next.js routing syntax", or any request for library/framework documentation.

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-07T18:33:55.247Z",
    "slug": "abdullahmalik17-context7-efficient",
    "source_url": "https://github.com/AbdullahMalik17/Cloud-Native-AI/tree/main/.claude/skills/context7-efficient",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "08b1fda56cecabd8ce9bfc95c017f5d522ce08bb3499713156e21c937d1090b7",
    "tree_hash": "6f4d8613e06100d988af221311d54aab482b0fd1f4c5ff26adb4794dc9abb788",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "context7-efficient",
    "description": "Fetches Context7 library documentation through shell scripts, then filters the response into concise code examples, API signatures, and notes.",
    "summary": "Fetch Context7 documentation with token-efficient shell filtering.",
    "icon": "📦",
    "version": "1.0.1",
    "author": "AbdullahMalik17",
    "license": "MIT",
    "tags": [
      "context7",
      "documentation",
      "mcp",
      "api-reference",
      "token-efficiency"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "network",
      "external_commands",
      "filesystem"
    ],
    "category": "documentation"
  },
  "security_audit": {
    "risk_level": "high",
    "is_blocked": false,
    "safe_to_publish": false,
    "analysis_status": "ok",
    "summary": "The skill has legitimate documentation-fetching intent, and many static hits are markdown backticks or Context7 reference text. Real risks remain from shell execution, shell=True stdio handling, unpinned npx package execution, unescaped JSON parameter construction, and predictable /tmp PID files. No prompt injection attempt was found in the reviewed files.",
    "remediation": [
      {
        "issue": "The MCP client executes --stdio command strings with shell=True.",
        "suggestion": "Replace shell=True with an argument array, parse commands with shlex only when needed, and allowlist the Context7 MCP command used by this skill.",
        "severity": "high"
      },
      {
        "issue": "Scripts execute an unpinned npx package for Context7 MCP.",
        "suggestion": "Pin @upstash/context7-mcp to a reviewed version or ship a lockfile-backed wrapper, and document the outbound network behavior.",
        "severity": "high"
      },
      {
        "issue": "JSON request bodies are assembled with shell interpolation.",
        "suggestion": "Build MCP parameters with Python json.dumps or jq, validate page and mode values, and escape library and topic strings structurally.",
        "severity": "medium"
      },
      {
        "issue": "Server lifecycle scripts trust predictable PID files in /tmp.",
        "suggestion": "Store PID files in a user-owned runtime directory, validate the port as a number, check process ownership, and avoid broad pkill patterns.",
        "severity": "medium"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "network",
        "evidence": [
          {
            "file": "references/context7-tools.md",
            "line_start": 169,
            "line_end": 169
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 146,
            "line_end": 146
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 271,
            "line_end": 271
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 314,
            "line_end": 314
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 323,
            "line_end": 323
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 328,
            "line_end": 328
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 333,
            "line_end": 333
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 33,
            "line_end": 33
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 10,
            "line_end": 10
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 16,
            "line_end": 16
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 20,
            "line_end": 20
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 23,
            "line_end": 23
          },
          {
            "file": "SKILL.md",
            "line_start": 201,
            "line_end": 201
          }
        ]
      },
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "scripts/extract-code-blocks.sh",
            "line_start": 9,
            "line_end": 18
          },
          {
            "file": "scripts/extract-code-blocks.sh",
            "line_start": 18,
            "line_end": 25
          },
          {
            "file": "scripts/extract-code-blocks.sh",
            "line_start": 25,
            "line_end": 27
          },
          {
            "file": "scripts/extract-code-blocks.sh",
            "line_start": 27,
            "line_end": 30
          },
          {
            "file": "scripts/extract-code-blocks.sh",
            "line_start": 30,
            "line_end": 38
          },
          {
            "file": "scripts/extract-code-blocks.sh",
            "line_start": 1,
            "line_end": 1
          },
          {
            "file": "scripts/extract-notes.sh",
            "line_start": 1,
            "line_end": 1
          },
          {
            "file": "scripts/extract-signatures.sh",
            "line_start": 16,
            "line_end": 16
          },
          {
            "file": "scripts/extract-signatures.sh",
            "line_start": 30,
            "line_end": 30
          },
          {
            "file": "scripts/extract-signatures.sh",
            "line_start": 38,
            "line_end": 38
          },
          {
            "file": "scripts/extract-signatures.sh",
            "line_start": 1,
            "line_end": 1
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 11,
            "line_end": 11
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 93,
            "line_end": 96
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 100,
            "line_end": 100
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 102,
            "line_end": 102
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 106,
            "line_end": 106
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 120,
            "line_end": 120
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 124,
            "line_end": 124
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 126,
            "line_end": 126
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 136,
            "line_end": 136
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 137,
            "line_end": 137
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 150,
            "line_end": 150
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 157,
            "line_end": 157
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 167,
            "line_end": 167
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 174,
            "line_end": 175
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 183,
            "line_end": 183
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 191,
            "line_end": 191
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 200,
            "line_end": 200
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 201,
            "line_end": 201
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 202,
            "line_end": 202
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 1,
            "line_end": 1
          },
          {
            "file": "scripts/fetch-raw.sh",
            "line_start": 13,
            "line_end": 19
          },
          {
            "file": "scripts/fetch-raw.sh",
            "line_start": 23,
            "line_end": 31
          },
          {
            "file": "scripts/fetch-raw.sh",
            "line_start": 35,
            "line_end": 35
          },
          {
            "file": "scripts/fetch-raw.sh",
            "line_start": 1,
            "line_end": 1
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 191,
            "line_end": 191
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 204,
            "line_end": 204
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 348,
            "line_end": 348
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 371,
            "line_end": 371
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 377,
            "line_end": 379
          },
          {
            "file": "scripts/start-server.sh",
            "line_start": 9,
            "line_end": 9
          },
          {
            "file": "scripts/start-server.sh",
            "line_start": 10,
            "line_end": 10
          },
          {
            "file": "scripts/start-server.sh",
            "line_start": 20,
            "line_end": 20
          },
          {
            "file": "scripts/start-server.sh",
            "line_start": 21,
            "line_end": 21
          },
          {
            "file": "scripts/start-server.sh",
            "line_start": 1,
            "line_end": 1
          },
          {
            "file": "scripts/stop-server.sh",
            "line_start": 9,
            "line_end": 9
          },
          {
            "file": "scripts/stop-server.sh",
            "line_start": 1,
            "line_end": 1
          },
          {
            "file": "SKILL.md",
            "line_start": 14,
            "line_end": 22
          },
          {
            "file": "SKILL.md",
            "line_start": 22,
            "line_end": 38
          },
          {
            "file": "SKILL.md",
            "line_start": 38,
            "line_end": 40
          },
          {
            "file": "SKILL.md",
            "line_start": 40,
            "line_end": 42
          },
          {
            "file": "SKILL.md",
            "line_start": 42,
            "line_end": 55
          },
          {
            "file": "SKILL.md",
            "line_start": 55,
            "line_end": 57
          },
          {
            "file": "SKILL.md",
            "line_start": 57,
            "line_end": 60
          },
          {
            "file": "SKILL.md",
            "line_start": 60,
            "line_end": 61
          },
          {
            "file": "SKILL.md",
            "line_start": 61,
            "line_end": 64
          },
          {
            "file": "SKILL.md",
            "line_start": 64,
            "line_end": 65
          },
          {
            "file": "SKILL.md",
            "line_start": 65,
            "line_end": 66
          },
          {
            "file": "SKILL.md",
            "line_start": 66,
            "line_end": 67
          },
          {
            "file": "SKILL.md",
            "line_start": 67,
            "line_end": 72
          },
          {
            "file": "SKILL.md",
            "line_start": 72,
            "line_end": 74
          },
          {
            "file": "SKILL.md",
            "line_start": 74,
            "line_end": 77
          },
          {
            "file": "SKILL.md",
            "line_start": 77,
            "line_end": 79
          },
          {
            "file": "SKILL.md",
            "line_start": 79,
            "line_end": 83
          },
          {
            "file": "SKILL.md",
            "line_start": 83,
            "line_end": 85
          },
          {
            "file": "SKILL.md",
            "line_start": 85,
            "line_end": 95
          },
          {
            "file": "SKILL.md",
            "line_start": 95,
            "line_end": 103
          },
          {
            "file": "SKILL.md",
            "line_start": 103,
            "line_end": 105
          },
          {
            "file": "SKILL.md",
            "line_start": 105,
            "line_end": 113
          },
          {
            "file": "SKILL.md",
            "line_start": 113,
            "line_end": 119
          },
          {
            "file": "SKILL.md",
            "line_start": 119,
            "line_end": 125
          },
          {
            "file": "SKILL.md",
            "line_start": 125,
            "line_end": 127
          },
          {
            "file": "SKILL.md",
            "line_start": 127,
            "line_end": 129
          },
          {
            "file": "SKILL.md",
            "line_start": 129,
            "line_end": 135
          },
          {
            "file": "SKILL.md",
            "line_start": 135,
            "line_end": 141
          },
          {
            "file": "SKILL.md",
            "line_start": 141,
            "line_end": 147
          },
          {
            "file": "SKILL.md",
            "line_start": 147,
            "line_end": 147
          },
          {
            "file": "SKILL.md",
            "line_start": 157,
            "line_end": 163
          },
          {
            "file": "SKILL.md",
            "line_start": 163,
            "line_end": 172
          },
          {
            "file": "SKILL.md",
            "line_start": 172,
            "line_end": 179
          },
          {
            "file": "SKILL.md",
            "line_start": 179,
            "line_end": 180
          },
          {
            "file": "SKILL.md",
            "line_start": 180,
            "line_end": 181
          },
          {
            "file": "SKILL.md",
            "line_start": 181,
            "line_end": 191
          },
          {
            "file": "SKILL.md",
            "line_start": 191,
            "line_end": 192
          },
          {
            "file": "SKILL.md",
            "line_start": 192,
            "line_end": 193
          },
          {
            "file": "SKILL.md",
            "line_start": 193,
            "line_end": 194
          },
          {
            "file": "SKILL.md",
            "line_start": 194,
            "line_end": 195
          },
          {
            "file": "SKILL.md",
            "line_start": 195,
            "line_end": 196
          }
        ]
      },
      {
        "factor": "filesystem",
        "evidence": [
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 96,
            "line_end": 96
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 99,
            "line_end": 99
          },
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 123,
            "line_end": 123
          },
          {
            "file": "scripts/fetch-raw.sh",
            "line_start": 38,
            "line_end": 38
          },
          {
            "file": "scripts/start-server.sh",
            "line_start": 9,
            "line_end": 9
          },
          {
            "file": "scripts/start-server.sh",
            "line_start": 20,
            "line_end": 20
          },
          {
            "file": "scripts/start-server.sh",
            "line_start": 6,
            "line_end": 6
          },
          {
            "file": "scripts/stop-server.sh",
            "line_start": 10,
            "line_end": 10
          },
          {
            "file": "scripts/stop-server.sh",
            "line_start": 12,
            "line_end": 12
          },
          {
            "file": "scripts/stop-server.sh",
            "line_start": 16,
            "line_end": 16
          },
          {
            "file": "scripts/stop-server.sh",
            "line_start": 25,
            "line_end": 25
          },
          {
            "file": "scripts/stop-server.sh",
            "line_start": 6,
            "line_end": 6
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "network:references/context7-tools.md:169:fetch-api-call",
        "category": "network",
        "severity": "low",
        "pattern": "Fetch API call",
        "file": "references/context7-tools.md",
        "line_start": 169,
        "line_end": 169,
        "snippet": "# Direct fetch (skip resolve step)"
      },
      {
        "id": "blocker:references/context7-tools.md:9:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/context7-tools.md",
        "line_start": 9,
        "line_end": 9,
        "snippet": "You MUST call this function before 'get-library-docs' to obtain a valid Context7-compatible library "
      },
      {
        "id": "blocker:references/context7-tools.md:40:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/context7-tools.md",
        "line_start": 40,
        "line_end": 40,
        "snippet": "-t resolve-library-id \\"
      },
      {
        "id": "blocker:references/context7-tools.md:45:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/context7-tools.md",
        "line_start": 45,
        "line_end": 45,
        "snippet": "-t resolve-library-id \\"
      },
      {
        "id": "blocker:references/context7-tools.md:50:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/context7-tools.md",
        "line_start": 50,
        "line_end": 50,
        "snippet": "-t resolve-library-id \\"
      },
      {
        "id": "blocker:references/context7-tools.md:156:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/context7-tools.md",
        "line_start": 156,
        "line_end": 156,
        "snippet": "-t resolve-library-id -p '{\"libraryName\": \"express\"}'"
      },
      {
        "id": "external_commands:scripts/extract-code-blocks.sh:9:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "scripts/extract-code-blocks.sh",
        "line_start": 9,
        "line_end": 18,
        "snippet": "# Use awk to extract code blocks between ``` markers"
      },
      {
        "id": "external_commands:scripts/extract-code-blocks.sh:18:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "scripts/extract-code-blocks.sh",
        "line_start": 18,
        "line_end": 25,
        "snippet": "/^```/ {"
      },
      {
        "id": "external_commands:scripts/extract-code-blocks.sh:25:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "scripts/extract-code-blocks.sh",
        "line_start": 25,
        "line_end": 27,
        "snippet": "print \"```\" lang"
      },
      {
        "id": "external_commands:scripts/extract-code-blocks.sh:27:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "scripts/extract-code-blocks.sh",
        "line_start": 27,
        "line_end": 30,
        "snippet": "print \"```\""
      },
      {
        "id": "external_commands:scripts/extract-code-blocks.sh:30:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "scripts/extract-code-blocks.sh",
        "line_start": 30,
        "line_end": 38,
        "snippet": "print \"```\\n\""
      },
      {
        "id": "external_commands:scripts/extract-code-blocks.sh:1:unix-shell-invocation",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Unix shell invocation",
        "file": "scripts/extract-code-blocks.sh",
        "line_start": 1,
        "line_end": 1,
        "snippet": "#!/bin/bash"
      },
      {
        "id": "external_commands:scripts/extract-notes.sh:1:unix-shell-invocation",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Unix shell invocation",
        "file": "scripts/extract-notes.sh",
        "line_start": 1,
        "line_end": 1,
        "snippet": "#!/bin/bash"
      },
      {
        "id": "external_commands:scripts/extract-signatures.sh:16:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "scripts/extract-signatures.sh",
        "line_start": 16,
        "line_end": 16,
        "snippet": "print \"- `\" $0 \"`\""
      },
      {
        "id": "external_commands:scripts/extract-signatures.sh:30:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "scripts/extract-signatures.sh",
        "line_start": 30,
        "line_end": 30,
        "snippet": "print \"- `\" sig \"`\""
      },
      {
        "id": "external_commands:scripts/extract-signatures.sh:38:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "scripts/extract-signatures.sh",
        "line_start": 38,
        "line_end": 38,
        "snippet": "print \"- `\" $0 \"`\""
      },
      {
        "id": "external_commands:scripts/extract-signatures.sh:1:unix-shell-invocation",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Unix shell invocation",
        "file": "scripts/extract-signatures.sh",
        "line_start": 1,
        "line_end": 1,
        "snippet": "#!/bin/bash"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:11:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-docs.sh",
        "line_start": 11,
        "line_end": 11,
        "snippet": "SCRIPT_DIR=\"$(cd \"$(dirname \"${BASH_SOURCE[0]}\")\" && pwd)\""
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:93:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-docs.sh",
        "line_start": 93,
        "line_end": 96,
        "snippet": "RESOLVE_JSON=$(python3 \"$SCRIPT_DIR/mcp-client.py\" call \\"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:100:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-docs.sh",
        "line_start": 100,
        "line_end": 100,
        "snippet": "RESOLVE_TEXT=$(echo \"$RESOLVE_JSON\" | jq -r '.content[0].text')"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:102:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-docs.sh",
        "line_start": 102,
        "line_end": 102,
        "snippet": "RESOLVE_TEXT=$(echo \"$RESOLVE_JSON\" | python3 -c 'import sys, json; data=json.load(sys.stdin); print"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:106:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-docs.sh",
        "line_start": 106,
        "line_end": 106,
        "snippet": "LIBRARY_ID=$(echo \"$RESOLVE_TEXT\" | grep -oP 'Context7-compatible library ID:\\s*\\K[/\\w.-]+' | head -"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:120:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-docs.sh",
        "line_start": 120,
        "line_end": 120,
        "snippet": "RAW_JSON=$(\"$SCRIPT_DIR/fetch-raw.sh\" \"$LIBRARY_ID\" \"$TOPIC\" \"$MODE\" \"$PAGE\")"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:124:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-docs.sh",
        "line_start": 124,
        "line_end": 124,
        "snippet": "RAW_TEXT=$(echo \"$RAW_JSON\" | jq -r '.content[0].text // empty')"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:126:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-docs.sh",
        "line_start": 126,
        "line_end": 126,
        "snippet": "RAW_TEXT=$(echo \"$RAW_JSON\" | python3 -c 'import sys, json; data=json.load(sys.stdin); print(data.ge"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:136:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-docs.sh",
        "line_start": 136,
        "line_end": 136,
        "snippet": "RAW_WORDS=$(echo \"$RAW_TEXT\" | wc -w)"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:137:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-docs.sh",
        "line_start": 137,
        "line_end": 137,
        "snippet": "RAW_TOKENS=$(echo \"$RAW_WORDS * 1.3\" | bc | cut -d. -f1)"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:150:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-docs.sh",
        "line_start": 150,
        "line_end": 150,
        "snippet": "CODE_BLOCKS=$(echo \"$RAW_TEXT\" | \"$SCRIPT_DIR/extract-code-blocks.sh\" 5)"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:157:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-docs.sh",
        "line_start": 157,
        "line_end": 157,
        "snippet": "SIGNATURES=$(echo \"$RAW_TEXT\" | \"$SCRIPT_DIR/extract-signatures.sh\" 3)"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:167:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-docs.sh",
        "line_start": 167,
        "line_end": 167,
        "snippet": "CODE_BLOCKS=$(echo \"$RAW_TEXT\" | \"$SCRIPT_DIR/extract-code-blocks.sh\" 2)"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:174:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-docs.sh",
        "line_start": 174,
        "line_end": 175,
        "snippet": "OVERVIEW=$(echo \"$RAW_TEXT\" | \\"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:183:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-docs.sh",
        "line_start": 183,
        "line_end": 183,
        "snippet": "NOTES=$(echo \"$RAW_TEXT\" | \"$SCRIPT_DIR/extract-notes.sh\" 3)"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:191:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-docs.sh",
        "line_start": 191,
        "line_end": 191,
        "snippet": "OUTPUT=$(echo \"$RAW_TEXT\" | head -c 500)"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:200:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-docs.sh",
        "line_start": 200,
        "line_end": 200,
        "snippet": "FILTERED_WORDS=$(echo -e \"$OUTPUT\" | wc -w)"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:201:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-docs.sh",
        "line_start": 201,
        "line_end": 201,
        "snippet": "FILTERED_TOKENS=$(echo \"$FILTERED_WORDS * 1.3\" | bc | cut -d. -f1)"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:202:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-docs.sh",
        "line_start": 202,
        "line_end": 202,
        "snippet": "SAVINGS=$(echo \"scale=1; (($RAW_TOKENS - $FILTERED_TOKENS) / $RAW_TOKENS) * 100\" | bc)"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:1:unix-shell-invocation",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Unix shell invocation",
        "file": "scripts/fetch-docs.sh",
        "line_start": 1,
        "line_end": 1,
        "snippet": "#!/bin/bash"
      },
      {
        "id": "filesystem:scripts/fetch-docs.sh:96:standard-device-file-access",
        "category": "filesystem",
        "severity": "low",
        "pattern": "Standard device file access",
        "file": "scripts/fetch-docs.sh",
        "line_start": 96,
        "line_end": 96,
        "snippet": "-p \"{\\\"libraryName\\\": \\\"$LIBRARY_NAME\\\"}\" 2>/dev/null)"
      },
      {
        "id": "filesystem:scripts/fetch-docs.sh:99:standard-device-file-access",
        "category": "filesystem",
        "severity": "low",
        "pattern": "Standard device file access",
        "file": "scripts/fetch-docs.sh",
        "line_start": 99,
        "line_end": 99,
        "snippet": "if command -v jq &> /dev/null; then"
      },
      {
        "id": "filesystem:scripts/fetch-docs.sh:123:standard-device-file-access",
        "category": "filesystem",
        "severity": "low",
        "pattern": "Standard device file access",
        "file": "scripts/fetch-docs.sh",
        "line_start": 123,
        "line_end": 123,
        "snippet": "if command -v jq &> /dev/null; then"
      },
      {
        "id": "blocker:scripts/fetch-docs.sh:27:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/fetch-docs.sh",
        "line_start": 27,
        "line_end": 27,
        "snippet": "--library-id ID    Context7 library ID (e.g., /reactjs/react.dev)"
      },
      {
        "id": "blocker:scripts/fetch-docs.sh:37:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/fetch-docs.sh",
        "line_start": 37,
        "line_end": 37,
        "snippet": "$0 --library-id /reactjs/react.dev --topic useState"
      },
      {
        "id": "blocker:scripts/fetch-docs.sh:43:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/fetch-docs.sh",
        "line_start": 43,
        "line_end": 43,
        "snippet": "$0 --library-id /prisma/docs --topic \"getting started\" --mode info"
      },
      {
        "id": "blocker:scripts/fetch-docs.sh:92:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/fetch-docs.sh",
        "line_start": 92,
        "line_end": 93,
        "snippet": "# Call resolve-library-id"
      },
      {
        "id": "blocker:scripts/fetch-docs.sh:95:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/fetch-docs.sh",
        "line_start": 95,
        "line_end": 95,
        "snippet": "-t resolve-library-id \\"
      },
      {
        "id": "blocker:scripts/fetch-docs.sh:113:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/fetch-docs.sh",
        "line_start": 113,
        "line_end": 113,
        "snippet": "echo \"Error: Must specify --library-id or --library\" >&2"
      },
      {
        "id": "external_commands:scripts/fetch-raw.sh:13:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-raw.sh",
        "line_start": 13,
        "line_end": 19,
        "snippet": "PARAMS=$(cat <<JSON"
      },
      {
        "id": "external_commands:scripts/fetch-raw.sh:23:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-raw.sh",
        "line_start": 23,
        "line_end": 31,
        "snippet": "PARAMS=$(cat <<JSON"
      },
      {
        "id": "external_commands:scripts/fetch-raw.sh:35:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/fetch-raw.sh",
        "line_start": 35,
        "line_end": 35,
        "snippet": "python3 \"$(dirname \"$0\")/mcp-client.py\" call \\"
      },
      {
        "id": "external_commands:scripts/fetch-raw.sh:1:unix-shell-invocation",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Unix shell invocation",
        "file": "scripts/fetch-raw.sh",
        "line_start": 1,
        "line_end": 1,
        "snippet": "#!/bin/bash"
      },
      {
        "id": "filesystem:scripts/fetch-raw.sh:38:standard-device-file-access",
        "category": "filesystem",
        "severity": "low",
        "pattern": "Standard device file access",
        "file": "scripts/fetch-raw.sh",
        "line_start": 38,
        "line_end": 38,
        "snippet": "-p \"$PARAMS\" 2>/dev/null"
      },
      {
        "id": "external_commands:scripts/mcp-client.py:191:python-subprocess-popen",
        "category": "external_commands",
        "severity": "high",
        "pattern": "Python subprocess.Popen",
        "file": "scripts/mcp-client.py",
        "line_start": 191,
        "line_end": 191,
        "snippet": "self._process: Optional[subprocess.Popen] = None"
      },
      {
        "id": "external_commands:scripts/mcp-client.py:204:python-subprocess-popen",
        "category": "external_commands",
        "severity": "high",
        "pattern": "Python subprocess.Popen",
        "file": "scripts/mcp-client.py",
        "line_start": 204,
        "line_end": 204,
        "snippet": "self._process = subprocess.Popen("
      },
      {
        "id": "external_commands:scripts/mcp-client.py:348:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "scripts/mcp-client.py",
        "line_start": 348,
        "line_end": 348,
        "snippet": "lines.append(f\"## `{name}`\\n\")"
      },
      {
        "id": "external_commands:scripts/mcp-client.py:371:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "scripts/mcp-client.py",
        "line_start": 371,
        "line_end": 371,
        "snippet": "lines.append(f\"- **`{prop_name}`** (`{prop_type}`){req_marker}: {prop_desc}\")"
      },
      {
        "id": "external_commands:scripts/mcp-client.py:377:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "scripts/mcp-client.py",
        "line_start": 377,
        "line_end": 379,
        "snippet": "lines.append(\"```json\")"
      },
      {
        "id": "network:scripts/mcp-client.py:146:http-client-library",
        "category": "network",
        "severity": "low",
        "pattern": "HTTP client library",
        "file": "scripts/mcp-client.py",
        "line_start": 146,
        "line_end": 146,
        "snippet": "def request(self, method: str, params: Optional[dict] = None) -> dict:"
      },
      {
        "id": "network:scripts/mcp-client.py:271:http-client-library",
        "category": "network",
        "severity": "low",
        "pattern": "HTTP client library",
        "file": "scripts/mcp-client.py",
        "line_start": 271,
        "line_end": 271,
        "snippet": "def request(self, method: str, params: Optional[dict] = None) -> dict:"
      },
      {
        "id": "network:scripts/mcp-client.py:314:http-client-library",
        "category": "network",
        "severity": "low",
        "pattern": "HTTP client library",
        "file": "scripts/mcp-client.py",
        "line_start": 314,
        "line_end": 314,
        "snippet": "result = self.transport.request(\"tools/list\")"
      },
      {
        "id": "network:scripts/mcp-client.py:323:http-client-library",
        "category": "network",
        "severity": "low",
        "pattern": "HTTP client library",
        "file": "scripts/mcp-client.py",
        "line_start": 323,
        "line_end": 323,
        "snippet": "result = self.transport.request(\"tools/call\", params)"
      },
      {
        "id": "network:scripts/mcp-client.py:328:http-client-library",
        "category": "network",
        "severity": "low",
        "pattern": "HTTP client library",
        "file": "scripts/mcp-client.py",
        "line_start": 328,
        "line_end": 328,
        "snippet": "result = self.transport.request(\"resources/list\")"
      },
      {
        "id": "network:scripts/mcp-client.py:333:http-client-library",
        "category": "network",
        "severity": "low",
        "pattern": "HTTP client library",
        "file": "scripts/mcp-client.py",
        "line_start": 333,
        "line_end": 333,
        "snippet": "result = self.transport.request(\"prompts/list\")"
      },
      {
        "id": "network:scripts/mcp-client.py:33:python-http-libraries",
        "category": "network",
        "severity": "low",
        "pattern": "Python HTTP libraries",
        "file": "scripts/mcp-client.py",
        "line_start": 33,
        "line_end": 33,
        "snippet": "from urllib.request import Request, urlopen"
      },
      {
        "id": "network:scripts/mcp-client.py:10:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "scripts/mcp-client.py",
        "line_start": 10,
        "line_end": 10,
        "snippet": "python mcp-client.py list --url http://localhost:8080"
      },
      {
        "id": "network:scripts/mcp-client.py:16:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "scripts/mcp-client.py",
        "line_start": 16,
        "line_end": 16,
        "snippet": "python mcp-client.py call --url http://localhost:8080 --tool create_issue \\"
      },
      {
        "id": "network:scripts/mcp-client.py:20:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "scripts/mcp-client.py",
        "line_start": 20,
        "line_end": 20,
        "snippet": "python mcp-client.py emit --url http://localhost:8080"
      },
      {
        "id": "network:scripts/mcp-client.py:23:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "scripts/mcp-client.py",
        "line_start": 23,
        "line_end": 23,
        "snippet": "python mcp-client.py emit --url http://localhost:8080 --format json"
      },
      {
        "id": "blocker:scripts/mcp-client.py:52:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 52,
        "line_end": 52,
        "snippet": "self._request_id = 0"
      },
      {
        "id": "blocker:scripts/mcp-client.py:57:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 57,
        "line_end": 57,
        "snippet": "self._request_id += 1"
      },
      {
        "id": "blocker:scripts/mcp-client.py:58:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 58,
        "line_end": 60,
        "snippet": "return self._request_id"
      },
      {
        "id": "blocker:scripts/mcp-client.py:88:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 88,
        "line_end": 88,
        "snippet": "self._session_id = resp.headers.get('Mcp-Session-Id')"
      },
      {
        "id": "blocker:scripts/mcp-client.py:137:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 137,
        "line_end": 139,
        "snippet": "headers[\"Mcp-Session-Id\"] = self._session_id"
      },
      {
        "id": "blocker:scripts/mcp-client.py:165:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 165,
        "line_end": 167,
        "snippet": "headers[\"Mcp-Session-Id\"] = self._session_id"
      },
      {
        "id": "blocker:scripts/mcp-client.py:190:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 190,
        "line_end": 190,
        "snippet": "self._request_id = 0"
      },
      {
        "id": "blocker:scripts/mcp-client.py:196:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 196,
        "line_end": 196,
        "snippet": "self._request_id += 1"
      },
      {
        "id": "blocker:scripts/mcp-client.py:197:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 197,
        "line_end": 199,
        "snippet": "return self._request_id"
      },
      {
        "id": "blocker:scripts/mcp-client.py:275:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 275,
        "line_end": 275,
        "snippet": "req_id = self._next_id()"
      },
      {
        "id": "blocker:scripts/mcp-client.py:286:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 286,
        "line_end": 287,
        "snippet": "# Wait for response with matching id"
      },
      {
        "id": "blocker:scripts/mcp-client.py:480:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "scripts/mcp-client.py",
        "line_start": 480,
        "line_end": 480,
        "snippet": "print(f\"Invalid JSON: {e}\", file=sys.stderr)"
      },
      {
        "id": "external_commands:scripts/start-server.sh:9:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/start-server.sh",
        "line_start": 9,
        "line_end": 9,
        "snippet": "if [ -f \"$PID_FILE\" ] && kill -0 $(cat \"$PID_FILE\") 2>/dev/null; then"
      },
      {
        "id": "external_commands:scripts/start-server.sh:10:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/start-server.sh",
        "line_start": 10,
        "line_end": 10,
        "snippet": "echo \"Context7 MCP already running on port $PORT (PID: $(cat $PID_FILE))\""
      },
      {
        "id": "external_commands:scripts/start-server.sh:20:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/start-server.sh",
        "line_start": 20,
        "line_end": 20,
        "snippet": "if kill -0 $(cat \"$PID_FILE\") 2>/dev/null; then"
      },
      {
        "id": "external_commands:scripts/start-server.sh:21:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/start-server.sh",
        "line_start": 21,
        "line_end": 21,
        "snippet": "echo \"Context7 MCP started on port $PORT (PID: $(cat $PID_FILE))\""
      },
      {
        "id": "external_commands:scripts/start-server.sh:1:unix-shell-invocation",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Unix shell invocation",
        "file": "scripts/start-server.sh",
        "line_start": 1,
        "line_end": 1,
        "snippet": "#!/bin/bash"
      },
      {
        "id": "filesystem:scripts/start-server.sh:9:standard-device-file-access",
        "category": "filesystem",
        "severity": "low",
        "pattern": "Standard device file access",
        "file": "scripts/start-server.sh",
        "line_start": 9,
        "line_end": 9,
        "snippet": "if [ -f \"$PID_FILE\" ] && kill -0 $(cat \"$PID_FILE\") 2>/dev/null; then"
      },
      {
        "id": "filesystem:scripts/start-server.sh:20:standard-device-file-access",
        "category": "filesystem",
        "severity": "low",
        "pattern": "Standard device file access",
        "file": "scripts/start-server.sh",
        "line_start": 20,
        "line_end": 20,
        "snippet": "if kill -0 $(cat \"$PID_FILE\") 2>/dev/null; then"
      },
      {
        "id": "filesystem:scripts/start-server.sh:6:temp-directory-access",
        "category": "filesystem",
        "severity": "medium",
        "pattern": "Temp directory access",
        "file": "scripts/start-server.sh",
        "line_start": 6,
        "line_end": 6,
        "snippet": "PID_FILE=\"/tmp/context7-mcp-${PORT}.pid\""
      },
      {
        "id": "external_commands:scripts/stop-server.sh:9:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "scripts/stop-server.sh",
        "line_start": 9,
        "line_end": 9,
        "snippet": "PID=$(cat \"$PID_FILE\")"
      },
      {
        "id": "external_commands:scripts/stop-server.sh:1:unix-shell-invocation",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Unix shell invocation",
        "file": "scripts/stop-server.sh",
        "line_start": 1,
        "line_end": 1,
        "snippet": "#!/bin/bash"
      },
      {
        "id": "filesystem:scripts/stop-server.sh:10:standard-device-file-access",
        "category": "filesystem",
        "severity": "low",
        "pattern": "Standard device file access",
        "file": "scripts/stop-server.sh",
        "line_start": 10,
        "line_end": 10,
        "snippet": "if kill -0 \"$PID\" 2>/dev/null; then"
      },
      {
        "id": "filesystem:scripts/stop-server.sh:12:standard-device-file-access",
        "category": "filesystem",
        "severity": "low",
        "pattern": "Standard device file access",
        "file": "scripts/stop-server.sh",
        "line_start": 12,
        "line_end": 12,
        "snippet": "kill \"$PID\" 2>/dev/null"
      },
      {
        "id": "filesystem:scripts/stop-server.sh:16:standard-device-file-access",
        "category": "filesystem",
        "severity": "low",
        "pattern": "Standard device file access",
        "file": "scripts/stop-server.sh",
        "line_start": 16,
        "line_end": 16,
        "snippet": "kill -9 \"$PID\" 2>/dev/null || true"
      },
      {
        "id": "filesystem:scripts/stop-server.sh:25:standard-device-file-access",
        "category": "filesystem",
        "severity": "low",
        "pattern": "Standard device file access",
        "file": "scripts/stop-server.sh",
        "line_start": 25,
        "line_end": 25,
        "snippet": "pkill -f \"context7-mcp.*--port.*${PORT}\" 2>/dev/null && echo \"Context7 MCP stopped\" || echo \"Context"
      },
      {
        "id": "filesystem:scripts/stop-server.sh:6:temp-directory-access",
        "category": "filesystem",
        "severity": "medium",
        "pattern": "Temp directory access",
        "file": "scripts/stop-server.sh",
        "line_start": 6,
        "line_end": 6,
        "snippet": "PID_FILE=\"/tmp/context7-mcp-${PORT}.pid\""
      },
      {
        "id": "external_commands:SKILL.md:14:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 14,
        "line_end": 22,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:22:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 22,
        "line_end": 38,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 38,
        "line_end": 40,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:40:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 40,
        "line_end": 42,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:42:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 42,
        "line_end": 55,
        "snippet": "The `--verbose` flag shows token savings statistics."
      },
      {
        "id": "external_commands:SKILL.md:55:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 55,
        "line_end": 57,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:57:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 57,
        "line_end": 60,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:60:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 60,
        "line_end": 61,
        "snippet": "- `--library <name>` - Library name (e.g., \"react\", \"nextjs\")"
      },
      {
        "id": "external_commands:SKILL.md:61:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 61,
        "line_end": 64,
        "snippet": "- `--library-id <id>` - Direct Context7 ID (faster, skips resolution)"
      },
      {
        "id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 64,
        "line_end": 65,
        "snippet": "- `--topic <topic>` - Specific feature to focus on"
      },
      {
        "id": "external_commands:SKILL.md:65:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 65,
        "line_end": 66,
        "snippet": "- `--mode <code|info>` - code for examples (default), info for concepts"
      },
      {
        "id": "external_commands:SKILL.md:66:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 66,
        "line_end": 67,
        "snippet": "- `--page <1-10>` - Pagination for more results"
      },
      {
        "id": "external_commands:SKILL.md:67:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 67,
        "line_end": 72,
        "snippet": "- `--verbose` - Show token savings statistics"
      },
      {
        "id": "external_commands:SKILL.md:72:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 72,
        "line_end": 74,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:74:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 74,
        "line_end": 77,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:77:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 77,
        "line_end": 79,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:79:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 79,
        "line_end": 83,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:83:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 83,
        "line_end": 85,
        "snippet": "Use `--library-id` for faster lookup (skips resolution):"
      },
      {
        "id": "external_commands:SKILL.md:85:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 85,
        "line_end": 95,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:95:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 95,
        "line_end": 103,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:103:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 103,
        "line_end": 105,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:105:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 105,
        "line_end": 113,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:113:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 113,
        "line_end": 119,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:119:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 119,
        "line_end": 125,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:125:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 125,
        "line_end": 127,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:127:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 127,
        "line_end": 129,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:129:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 129,
        "line_end": 135,
        "snippet": "Using `--library-id` is faster when you know the exact ID."
      },
      {
        "id": "external_commands:SKILL.md:135:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 135,
        "line_end": 141,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:141:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 141,
        "line_end": 147,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:147:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 147,
        "line_end": 147,
        "snippet": "1. `fetch-docs.sh` calls `fetch-raw.sh` (which uses `mcp-client.py`)"
      },
      {
        "id": "external_commands:SKILL.md:157:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 157,
        "line_end": 163,
        "snippet": "**Do NOT use `mcp-client.py` directly** - it bypasses filtering and wastes tokens."
      },
      {
        "id": "external_commands:SKILL.md:163:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 163,
        "line_end": 172,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:172:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 172,
        "line_end": 179,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:179:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 179,
        "line_end": 180,
        "snippet": "| No results | Use `--mode info` or broader topic |"
      },
      {
        "id": "external_commands:SKILL.md:180:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 180,
        "line_end": 181,
        "snippet": "| Need more examples | Increase page: `--page 2` |"
      },
      {
        "id": "external_commands:SKILL.md:181:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 181,
        "line_end": 191,
        "snippet": "| Want full context | Use `--mode info` for explanations |"
      },
      {
        "id": "external_commands:SKILL.md:191:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 191,
        "line_end": 192,
        "snippet": "- `mcp-client.py` - Universal MCP client (foundation)"
      },
      {
        "id": "external_commands:SKILL.md:192:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 192,
        "line_end": 193,
        "snippet": "- `fetch-raw.sh` - MCP wrapper"
      },
      {
        "id": "external_commands:SKILL.md:193:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 193,
        "line_end": 194,
        "snippet": "- `extract-code-blocks.sh` - Code example filter (awk)"
      },
      {
        "id": "external_commands:SKILL.md:194:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 194,
        "line_end": 195,
        "snippet": "- `extract-signatures.sh` - API signature filter (awk)"
      },
      {
        "id": "external_commands:SKILL.md:195:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 195,
        "line_end": 196,
        "snippet": "- `extract-notes.sh` - Important notes filter (grep)"
      },
      {
        "id": "network:SKILL.md:201:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 201,
        "line_end": 201,
        "snippet": "Based on [Anthropic's \"Code Execution with MCP\" blog post](https://www.anthropic.com/engineering/cod"
      },
      {
        "id": "blocker:SKILL.md:61:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 61,
        "line_end": 61,
        "snippet": "- `--library-id <id>` - Direct Context7 ID (faster, skips resolution)"
      },
      {
        "id": "blocker:SKILL.md:126:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 126,
        "line_end": 126,
        "snippet": "bash scripts/fetch-docs.sh --library-id /vercel/next.js --topic routing"
      }
    ],
    "finding_verdicts": [
      {
        "id": "network:references/context7-tools.md:169:fetch-api-call",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The word fetch appears in Context7 usage documentation, not in runtime Fetch API code. The markdown file does not implement a network request."
      },
      {
        "id": "blocker:references/context7-tools.md:9:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "This is Context7 tool reference documentation or an example command, not host reconnaissance or privileged system inspection."
      },
      {
        "id": "blocker:references/context7-tools.md:40:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "This is Context7 tool reference documentation or an example command, not host reconnaissance or privileged system inspection."
      },
      {
        "id": "blocker:references/context7-tools.md:45:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "This is Context7 tool reference documentation or an example command, not host reconnaissance or privileged system inspection."
      },
      {
        "id": "blocker:references/context7-tools.md:50:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "This is Context7 tool reference documentation or an example command, not host reconnaissance or privileged system inspection."
      },
      {
        "id": "blocker:references/context7-tools.md:156:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "This is Context7 tool reference documentation or an example command, not host reconnaissance or privileged system inspection."
      },
      {
        "id": "external_commands:scripts/extract-code-blocks.sh:9:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:scripts/extract-code-blocks.sh:18:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:scripts/extract-code-blocks.sh:25:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:scripts/extract-code-blocks.sh:27:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:scripts/extract-code-blocks.sh:30:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:scripts/extract-code-blocks.sh:1:unix-shell-invocation",
        "verdict": "false_positive",
        "confidence": 0.84,
        "reason": "This helper shell script applies fixed text filters to stdin with quoted arguments. It does not build or execute user-controlled command strings."
      },
      {
        "id": "external_commands:scripts/extract-notes.sh:1:unix-shell-invocation",
        "verdict": "false_positive",
        "confidence": 0.84,
        "reason": "This helper shell script applies fixed text filters to stdin with quoted arguments. It does not build or execute user-controlled command strings."
      },
      {
        "id": "external_commands:scripts/extract-signatures.sh:16:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:scripts/extract-signatures.sh:30:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:scripts/extract-signatures.sh:38:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:scripts/extract-signatures.sh:1:unix-shell-invocation",
        "verdict": "false_positive",
        "confidence": 0.84,
        "reason": "This helper shell script applies fixed text filters to stdin with quoted arguments. It does not build or execute user-controlled command strings."
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:11:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.83,
        "reason": "The command substitution performs local path discovery, parsing, or text filtering with fixed commands. Variables are quoted and no shell eval is used."
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:93:shell-command-substitution",
        "verdict": "confirmed",
        "confidence": 0.82,
        "reason": "This command substitution runs mcp-client.py with stdio command npx -y @upstash/context7-mcp to resolve a user-provided library name. It executes external npm tooling and sends request data to Context7.",
        "severity": "medium"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:100:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.83,
        "reason": "The command substitution performs local path discovery, parsing, or text filtering with fixed commands. Variables are quoted and no shell eval is used."
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:102:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.83,
        "reason": "The command substitution performs local path discovery, parsing, or text filtering with fixed commands. Variables are quoted and no shell eval is used."
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:106:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.83,
        "reason": "The command substitution performs local path discovery, parsing, or text filtering with fixed commands. Variables are quoted and no shell eval is used."
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:120:shell-command-substitution",
        "verdict": "confirmed",
        "confidence": 0.8,
        "reason": "This line delegates to fetch-raw.sh, which launches the Context7 MCP command. Arguments are quoted, but the pipeline still executes external tooling and contacts Context7.",
        "severity": "medium"
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:124:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.83,
        "reason": "The command substitution performs local path discovery, parsing, or text filtering with fixed commands. Variables are quoted and no shell eval is used."
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:126:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.83,
        "reason": "The command substitution performs local path discovery, parsing, or text filtering with fixed commands. Variables are quoted and no shell eval is used."
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:136:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.83,
        "reason": "The command substitution performs local path discovery, parsing, or text filtering with fixed commands. Variables are quoted and no shell eval is used."
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:137:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.83,
        "reason": "The command substitution performs local path discovery, parsing, or text filtering with fixed commands. Variables are quoted and no shell eval is used."
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:150:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.83,
        "reason": "The command substitution performs local path discovery, parsing, or text filtering with fixed commands. Variables are quoted and no shell eval is used."
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:157:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.83,
        "reason": "The command substitution performs local path discovery, parsing, or text filtering with fixed commands. Variables are quoted and no shell eval is used."
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:167:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.83,
        "reason": "The command substitution performs local path discovery, parsing, or text filtering with fixed commands. Variables are quoted and no shell eval is used."
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:174:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.83,
        "reason": "The command substitution performs local path discovery, parsing, or text filtering with fixed commands. Variables are quoted and no shell eval is used."
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:183:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.83,
        "reason": "The command substitution performs local path discovery, parsing, or text filtering with fixed commands. Variables are quoted and no shell eval is used."
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:191:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.83,
        "reason": "The command substitution performs local path discovery, parsing, or text filtering with fixed commands. Variables are quoted and no shell eval is used."
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:200:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.83,
        "reason": "The command substitution performs local path discovery, parsing, or text filtering with fixed commands. Variables are quoted and no shell eval is used."
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:201:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.83,
        "reason": "The command substitution performs local path discovery, parsing, or text filtering with fixed commands. Variables are quoted and no shell eval is used."
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:202:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.83,
        "reason": "The command substitution performs local path discovery, parsing, or text filtering with fixed commands. Variables are quoted and no shell eval is used."
      },
      {
        "id": "external_commands:scripts/fetch-docs.sh:1:unix-shell-invocation",
        "verdict": "confirmed",
        "confidence": 0.78,
        "reason": "This shell orchestrator invokes Python, local filters, and Context7 MCP through npx. The behavior is expected, but it is a real external command and network surface.",
        "severity": "medium"
      },
      {
        "id": "filesystem:scripts/fetch-docs.sh:96:standard-device-file-access",
        "verdict": "false_positive",
        "confidence": 0.86,
        "reason": "The matched text is stderr redirection to /dev/null or a local tool availability check. It does not read sensitive device files or exfiltrate data."
      },
      {
        "id": "filesystem:scripts/fetch-docs.sh:99:standard-device-file-access",
        "verdict": "false_positive",
        "confidence": 0.86,
        "reason": "The matched text is stderr redirection to /dev/null or a local tool availability check. It does not read sensitive device files or exfiltrate data."
      },
      {
        "id": "filesystem:scripts/fetch-docs.sh:123:standard-device-file-access",
        "verdict": "false_positive",
        "confidence": 0.86,
        "reason": "The matched text is stderr redirection to /dev/null or a local tool availability check. It does not read sensitive device files or exfiltrate data."
      },
      {
        "id": "blocker:scripts/fetch-docs.sh:27:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "This is Context7 tool reference documentation or an example command, not host reconnaissance or privileged system inspection."
      },
      {
        "id": "blocker:scripts/fetch-docs.sh:37:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "This is Context7 tool reference documentation or an example command, not host reconnaissance or privileged system inspection."
      },
      {
        "id": "blocker:scripts/fetch-docs.sh:43:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "This is Context7 tool reference documentation or an example command, not host reconnaissance or privileged system inspection."
      },
      {
        "id": "blocker:scripts/fetch-docs.sh:92:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "This is Context7 tool reference documentation or an example command, not host reconnaissance or privileged system inspection."
      },
      {
        "id": "blocker:scripts/fetch-docs.sh:95:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "This is Context7 tool reference documentation or an example command, not host reconnaissance or privileged system inspection."
      },
      {
        "id": "blocker:scripts/fetch-docs.sh:113:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "This is Context7 tool reference documentation or an example command, not host reconnaissance or privileged system inspection."
      },
      {
        "id": "external_commands:scripts/fetch-raw.sh:13:shell-command-substitution",
        "verdict": "confirmed",
        "confidence": 0.68,
        "reason": "The heredoc interpolates library ID, mode, and page values into JSON without structured escaping. Quoting prevents shell injection, but malformed input can alter or break MCP parameters.",
        "severity": "medium"
      },
      {
        "id": "external_commands:scripts/fetch-raw.sh:23:shell-command-substitution",
        "verdict": "confirmed",
        "confidence": 0.68,
        "reason": "The topic variant also interpolates user-controlled values into JSON without structured escaping. This can alter the MCP request body even though it is not direct shell injection.",
        "severity": "medium"
      },
      {
        "id": "external_commands:scripts/fetch-raw.sh:35:shell-command-substitution",
        "verdict": "confirmed",
        "confidence": 0.82,
        "reason": "This invokes mcp-client.py with a fixed stdio npx Context7 command. External npm package execution and outbound Context7 access are real risks.",
        "severity": "medium"
      },
      {
        "id": "external_commands:scripts/fetch-raw.sh:1:unix-shell-invocation",
        "verdict": "confirmed",
        "confidence": 0.78,
        "reason": "This shell wrapper calls mcp-client.py to run Context7 MCP through npx. That creates an external command and network dependency for each documentation fetch.",
        "severity": "medium"
      },
      {
        "id": "filesystem:scripts/fetch-raw.sh:38:standard-device-file-access",
        "verdict": "false_positive",
        "confidence": 0.86,
        "reason": "The matched text is stderr redirection to /dev/null or a local tool availability check. It does not read sensitive device files or exfiltrate data."
      },
      {
        "id": "external_commands:scripts/mcp-client.py:191:python-subprocess-popen",
        "verdict": "false_positive",
        "confidence": 0.88,
        "reason": "This line is a type annotation for a Popen field and does not start a process. The actual process launch is separately confirmed at line 204."
      },
      {
        "id": "external_commands:scripts/mcp-client.py:204:python-subprocess-popen",
        "verdict": "confirmed",
        "confidence": 0.94,
        "reason": "subprocess.Popen receives self.command with shell=True, and the command comes from the CLI --stdio option. If untrusted input reaches this option, arbitrary shell command execution is possible.",
        "severity": "high"
      },
      {
        "id": "external_commands:scripts/mcp-client.py:348:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks are literal Markdown formatting emitted into generated documentation. They are not Python, Ruby, or shell command execution."
      },
      {
        "id": "external_commands:scripts/mcp-client.py:371:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks are literal Markdown formatting emitted into generated documentation. They are not Python, Ruby, or shell command execution."
      },
      {
        "id": "external_commands:scripts/mcp-client.py:377:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks are literal Markdown formatting emitted into generated documentation. They are not Python, Ruby, or shell command execution."
      },
      {
        "id": "network:scripts/mcp-client.py:146:http-client-library",
        "verdict": "confirmed",
        "confidence": 0.76,
        "reason": "The client can send JSON-RPC requests to a configured MCP transport, including HTTP URLs. This is expected functionality, but it is real outbound network behavior with request parameters.",
        "severity": "low"
      },
      {
        "id": "network:scripts/mcp-client.py:271:http-client-library",
        "verdict": "false_positive",
        "confidence": 0.8,
        "reason": "This stdio request method writes JSON-RPC to an already-started subprocess, not an HTTP client call. Process execution risk is covered by the Popen finding."
      },
      {
        "id": "network:scripts/mcp-client.py:314:http-client-library",
        "verdict": "confirmed",
        "confidence": 0.76,
        "reason": "The client can send JSON-RPC requests to a configured MCP transport, including HTTP URLs. This is expected functionality, but it is real outbound network behavior with request parameters.",
        "severity": "low"
      },
      {
        "id": "network:scripts/mcp-client.py:323:http-client-library",
        "verdict": "confirmed",
        "confidence": 0.76,
        "reason": "The client can send JSON-RPC requests to a configured MCP transport, including HTTP URLs. This is expected functionality, but it is real outbound network behavior with request parameters.",
        "severity": "low"
      },
      {
        "id": "network:scripts/mcp-client.py:328:http-client-library",
        "verdict": "confirmed",
        "confidence": 0.76,
        "reason": "The client can send JSON-RPC requests to a configured MCP transport, including HTTP URLs. This is expected functionality, but it is real outbound network behavior with request parameters.",
        "severity": "low"
      },
      {
        "id": "network:scripts/mcp-client.py:333:http-client-library",
        "verdict": "confirmed",
        "confidence": 0.76,
        "reason": "The client can send JSON-RPC requests to a configured MCP transport, including HTTP URLs. This is expected functionality, but it is real outbound network behavior with request parameters.",
        "severity": "low"
      },
      {
        "id": "network:scripts/mcp-client.py:33:python-http-libraries",
        "verdict": "false_positive",
        "confidence": 0.78,
        "reason": "Importing an HTTP library is not itself a network operation. The actual outbound request behavior is evaluated on the transport request methods."
      },
      {
        "id": "network:scripts/mcp-client.py:10:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The hardcoded URL appears only in a usage docstring for localhost examples. It is not an external endpoint used by the skill at runtime."
      },
      {
        "id": "network:scripts/mcp-client.py:16:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The hardcoded URL appears only in a usage docstring for localhost examples. It is not an external endpoint used by the skill at runtime."
      },
      {
        "id": "network:scripts/mcp-client.py:20:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The hardcoded URL appears only in a usage docstring for localhost examples. It is not an external endpoint used by the skill at runtime."
      },
      {
        "id": "network:scripts/mcp-client.py:23:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The hardcoded URL appears only in a usage docstring for localhost examples. It is not an external endpoint used by the skill at runtime."
      },
      {
        "id": "blocker:scripts/mcp-client.py:52:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "These lines manage JSON-RPC request IDs, MCP session headers, or a local JSON parse error. They do not inspect host configuration or enumerate the system."
      },
      {
        "id": "blocker:scripts/mcp-client.py:57:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "These lines manage JSON-RPC request IDs, MCP session headers, or a local JSON parse error. They do not inspect host configuration or enumerate the system."
      },
      {
        "id": "blocker:scripts/mcp-client.py:58:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "These lines manage JSON-RPC request IDs, MCP session headers, or a local JSON parse error. They do not inspect host configuration or enumerate the system."
      },
      {
        "id": "blocker:scripts/mcp-client.py:88:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "These lines manage JSON-RPC request IDs, MCP session headers, or a local JSON parse error. They do not inspect host configuration or enumerate the system."
      },
      {
        "id": "blocker:scripts/mcp-client.py:137:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "These lines manage JSON-RPC request IDs, MCP session headers, or a local JSON parse error. They do not inspect host configuration or enumerate the system."
      },
      {
        "id": "blocker:scripts/mcp-client.py:165:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "These lines manage JSON-RPC request IDs, MCP session headers, or a local JSON parse error. They do not inspect host configuration or enumerate the system."
      },
      {
        "id": "blocker:scripts/mcp-client.py:190:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "These lines manage JSON-RPC request IDs, MCP session headers, or a local JSON parse error. They do not inspect host configuration or enumerate the system."
      },
      {
        "id": "blocker:scripts/mcp-client.py:196:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "These lines manage JSON-RPC request IDs, MCP session headers, or a local JSON parse error. They do not inspect host configuration or enumerate the system."
      },
      {
        "id": "blocker:scripts/mcp-client.py:197:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "These lines manage JSON-RPC request IDs, MCP session headers, or a local JSON parse error. They do not inspect host configuration or enumerate the system."
      },
      {
        "id": "blocker:scripts/mcp-client.py:275:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "These lines manage JSON-RPC request IDs, MCP session headers, or a local JSON parse error. They do not inspect host configuration or enumerate the system."
      },
      {
        "id": "blocker:scripts/mcp-client.py:286:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "These lines manage JSON-RPC request IDs, MCP session headers, or a local JSON parse error. They do not inspect host configuration or enumerate the system."
      },
      {
        "id": "blocker:scripts/mcp-client.py:480:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "These lines manage JSON-RPC request IDs, MCP session headers, or a local JSON parse error. They do not inspect host configuration or enumerate the system."
      },
      {
        "id": "external_commands:scripts/start-server.sh:9:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.72,
        "reason": "This command substitution reads the PID file for a process-existence check or status message. The broader predictable temp-file risk is tracked separately."
      },
      {
        "id": "external_commands:scripts/start-server.sh:10:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.72,
        "reason": "This command substitution reads the PID file for a process-existence check or status message. The broader predictable temp-file risk is tracked separately."
      },
      {
        "id": "external_commands:scripts/start-server.sh:20:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.72,
        "reason": "This command substitution reads the PID file for a process-existence check or status message. The broader predictable temp-file risk is tracked separately."
      },
      {
        "id": "external_commands:scripts/start-server.sh:21:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.72,
        "reason": "This command substitution reads the PID file for a process-existence check or status message. The broader predictable temp-file risk is tracked separately."
      },
      {
        "id": "external_commands:scripts/start-server.sh:1:unix-shell-invocation",
        "verdict": "confirmed",
        "confidence": 0.75,
        "reason": "This shell script starts an external Context7 MCP server with npx and records PID state. That is expected behavior, but it is a real external command surface.",
        "severity": "medium"
      },
      {
        "id": "filesystem:scripts/start-server.sh:9:standard-device-file-access",
        "verdict": "false_positive",
        "confidence": 0.86,
        "reason": "The matched text is stderr redirection to /dev/null or a local tool availability check. It does not read sensitive device files or exfiltrate data."
      },
      {
        "id": "filesystem:scripts/start-server.sh:20:standard-device-file-access",
        "verdict": "false_positive",
        "confidence": 0.86,
        "reason": "The matched text is stderr redirection to /dev/null or a local tool availability check. It does not read sensitive device files or exfiltrate data."
      },
      {
        "id": "filesystem:scripts/start-server.sh:6:temp-directory-access",
        "verdict": "confirmed",
        "confidence": 0.78,
        "reason": "The script uses a predictable PID file under /tmp derived from the port value. A stale or locally tampered file can influence server lifecycle checks.",
        "severity": "medium"
      },
      {
        "id": "external_commands:scripts/stop-server.sh:9:shell-command-substitution",
        "verdict": "confirmed",
        "confidence": 0.82,
        "reason": "The PID is read from a predictable /tmp file and later used for kill operations. If that file is stale or tampered with, the script can target the wrong process.",
        "severity": "medium"
      },
      {
        "id": "external_commands:scripts/stop-server.sh:1:unix-shell-invocation",
        "verdict": "confirmed",
        "confidence": 0.78,
        "reason": "This shell script terminates processes based on a PID file or pkill pattern. Process termination is a real operational risk if inputs or PID state are wrong.",
        "severity": "medium"
      },
      {
        "id": "filesystem:scripts/stop-server.sh:10:standard-device-file-access",
        "verdict": "confirmed",
        "confidence": 0.68,
        "reason": "This checks a PID loaded from a mutable /tmp file. The check itself is not destructive, but it relies on untrusted process-control state.",
        "severity": "low"
      },
      {
        "id": "filesystem:scripts/stop-server.sh:12:standard-device-file-access",
        "verdict": "confirmed",
        "confidence": 0.82,
        "reason": "This sends a signal to the PID read from the predictable /tmp file. If the PID file is stale or tampered with, the wrong process can be terminated.",
        "severity": "medium"
      },
      {
        "id": "filesystem:scripts/stop-server.sh:16:standard-device-file-access",
        "verdict": "confirmed",
        "confidence": 0.82,
        "reason": "This force-kills the PID read from the predictable /tmp file. A stale or tampered PID file can cause unintended process termination.",
        "severity": "medium"
      },
      {
        "id": "filesystem:scripts/stop-server.sh:25:standard-device-file-access",
        "verdict": "confirmed",
        "confidence": 0.74,
        "reason": "The fallback pkill pattern includes an unvalidated port value. A crafted value can broaden the match against Context7 MCP command lines.",
        "severity": "medium"
      },
      {
        "id": "filesystem:scripts/stop-server.sh:6:temp-directory-access",
        "verdict": "confirmed",
        "confidence": 0.82,
        "reason": "The predictable /tmp PID path is trusted as process-control state. This can be influenced by stale files or local tampering.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:14:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:22:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:40:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:42:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:55:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:57:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:60:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:61:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:65:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:66:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:67:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:72:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:74:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:77:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:79:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:83:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:85:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:95:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:103:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:105:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:113:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:119:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:125:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:127:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:129:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:135:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:141:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:147:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:157:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:163:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:172:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:179:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:180:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:181:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:191:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:192:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:193:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:194:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "external_commands:SKILL.md:195:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The matched backticks are Markdown fences or inline formatting, not shell or Ruby command execution. No runtime command is launched by this line."
      },
      {
        "id": "network:SKILL.md:201:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The URL is a documentation citation in the skill README. It does not cause runtime network access."
      },
      {
        "id": "blocker:SKILL.md:61:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "This is Context7 tool reference documentation or an example command, not host reconnaissance or privileged system inspection."
      },
      {
        "id": "blocker:SKILL.md:126:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "This is Context7 tool reference documentation or an example command, not host reconnaissance or privileged system inspection."
      }
    ],
    "semantic_findings": [
      {
        "title": "User-Controlled Stdio Command Execution",
        "description": "The MCP client exposes a --stdio option and passes that command string to subprocess.Popen with shell=True. This turns the helper into a general shell execution wrapper if untrusted input controls the stdio command.",
        "severity": "high",
        "locations": [
          {
            "file": "scripts/mcp-client.py",
            "line_start": 204,
            "line_end": 206
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 422,
            "line_end": 423
          }
        ],
        "confidence": 0.91,
        "confidence_reasoning": "The command is accepted from a CLI argument and executed through shell=True. The code path is direct and does not apply an allowlist or argument array."
      },
      {
        "title": "Unpinned NPM MCP Server Execution",
        "description": "The scripts run npx -y @upstash/context7-mcp without a pinned package version. This can execute changed remote package code during documentation fetches or server startup.",
        "severity": "high",
        "locations": [
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 93,
            "line_end": 96
          },
          {
            "file": "scripts/fetch-raw.sh",
            "line_start": 35,
            "line_end": 38
          },
          {
            "file": "scripts/start-server.sh",
            "line_start": 15,
            "line_end": 15
          }
        ],
        "confidence": 0.9,
        "confidence_reasoning": "Multiple scripts invoke the same unversioned npx package. The behavior is intentional but creates a clear supply-chain execution risk."
      },
      {
        "title": "Unescaped JSON Parameter Construction",
        "description": "Shell heredocs and inline strings interpolate library, topic, mode, and page values into JSON without json.dumps or another structured encoder. Malformed input can alter or break MCP parameters.",
        "severity": "medium",
        "locations": [
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 93,
            "line_end": 96
          },
          {
            "file": "scripts/fetch-raw.sh",
            "line_start": 13,
            "line_end": 18
          },
          {
            "file": "scripts/fetch-raw.sh",
            "line_start": 23,
            "line_end": 30
          }
        ],
        "confidence": 0.78,
        "confidence_reasoning": "The variables are quoted for the shell, so direct command injection is unlikely. They are still inserted into JSON syntax without escaping or type validation."
      },
      {
        "title": "Predictable Temporary PID File Controls Process Termination",
        "description": "The server control scripts use predictable /tmp PID files and then trust those files when checking or killing processes. Stale or locally modified files can affect which process is targeted.",
        "severity": "medium",
        "locations": [
          {
            "file": "scripts/start-server.sh",
            "line_start": 6,
            "line_end": 6
          },
          {
            "file": "scripts/stop-server.sh",
            "line_start": 6,
            "line_end": 6
          },
          {
            "file": "scripts/stop-server.sh",
            "line_start": 9,
            "line_end": 16
          },
          {
            "file": "scripts/stop-server.sh",
            "line_start": 25,
            "line_end": 25
          }
        ],
        "confidence": 0.82,
        "confidence_reasoning": "The PID file path is deterministic and stored under /tmp, and stop-server.sh sends normal and forced kill signals based on that state. The impact depends on local filesystem access and execution privileges."
      }
    ],
    "critical_findings": [],
    "high_findings": [
      {
        "title": "Python subprocess.Popen",
        "description": "self._process = subprocess.Popen(",
        "locations": [
          {
            "file": "scripts/mcp-client.py",
            "line_start": 204,
            "line_end": 204
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "high",
        "confidence": 0.94,
        "confidence_reasoning": "subprocess.Popen receives self.command with shell=True, and the command comes from the CLI --stdio option. If untrusted input reaches this option, arbitrary shell command execution is possible."
      },
      {
        "title": "User-Controlled Stdio Command Execution",
        "description": "The MCP client exposes a --stdio option and passes that command string to subprocess.Popen with shell=True. This turns the helper into a general shell execution wrapper if untrusted input controls the stdio command.",
        "locations": [
          {
            "file": "scripts/mcp-client.py",
            "line_start": 204,
            "line_end": 206
          },
          {
            "file": "scripts/mcp-client.py",
            "line_start": 422,
            "line_end": 423
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "high",
        "confidence": 0.91,
        "confidence_reasoning": "The command is accepted from a CLI argument and executed through shell=True. The code path is direct and does not apply an allowlist or argument array."
      },
      {
        "title": "Unpinned NPM MCP Server Execution",
        "description": "The scripts run npx -y @upstash/context7-mcp without a pinned package version. This can execute changed remote package code during documentation fetches or server startup.",
        "locations": [
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 93,
            "line_end": 96
          },
          {
            "file": "scripts/fetch-raw.sh",
            "line_start": 35,
            "line_end": 38
          },
          {
            "file": "scripts/start-server.sh",
            "line_start": 15,
            "line_end": 15
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "high",
        "confidence": 0.9,
        "confidence_reasoning": "Multiple scripts invoke the same unversioned npx package. The behavior is intentional but creates a clear supply-chain execution risk."
      }
    ],
    "medium_findings": [
      {
        "title": "Shell command substitution",
        "description": "RESOLVE_JSON=$(python3 \"$SCRIPT_DIR/mcp-client.py\" call \\",
        "locations": [
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 93,
            "line_end": 96
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.82,
        "confidence_reasoning": "This command substitution runs mcp-client.py with stdio command npx -y @upstash/context7-mcp to resolve a user-provided library name. It executes external npm tooling and sends request data to Context7."
      },
      {
        "title": "Shell command substitution",
        "description": "RAW_JSON=$(\"$SCRIPT_DIR/fetch-raw.sh\" \"$LIBRARY_ID\" \"$TOPIC\" \"$MODE\" \"$PAGE\")",
        "locations": [
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 120,
            "line_end": 120
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.8,
        "confidence_reasoning": "This line delegates to fetch-raw.sh, which launches the Context7 MCP command. Arguments are quoted, but the pipeline still executes external tooling and contacts Context7."
      },
      {
        "title": "Unix shell invocation",
        "description": "#!/bin/bash",
        "locations": [
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 1,
            "line_end": 1
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.78,
        "confidence_reasoning": "This shell orchestrator invokes Python, local filters, and Context7 MCP through npx. The behavior is expected, but it is a real external command and network surface."
      },
      {
        "title": "Shell command substitution",
        "description": "PARAMS=$(cat <<JSON",
        "locations": [
          {
            "file": "scripts/fetch-raw.sh",
            "line_start": 13,
            "line_end": 19
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.68,
        "confidence_reasoning": "The heredoc interpolates library ID, mode, and page values into JSON without structured escaping. Quoting prevents shell injection, but malformed input can alter or break MCP parameters."
      },
      {
        "title": "Shell command substitution",
        "description": "PARAMS=$(cat <<JSON",
        "locations": [
          {
            "file": "scripts/fetch-raw.sh",
            "line_start": 23,
            "line_end": 31
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.68,
        "confidence_reasoning": "The topic variant also interpolates user-controlled values into JSON without structured escaping. This can alter the MCP request body even though it is not direct shell injection."
      },
      {
        "title": "Shell command substitution",
        "description": "python3 \"$(dirname \"$0\")/mcp-client.py\" call \\",
        "locations": [
          {
            "file": "scripts/fetch-raw.sh",
            "line_start": 35,
            "line_end": 35
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.82,
        "confidence_reasoning": "This invokes mcp-client.py with a fixed stdio npx Context7 command. External npm package execution and outbound Context7 access are real risks."
      },
      {
        "title": "Unix shell invocation",
        "description": "#!/bin/bash",
        "locations": [
          {
            "file": "scripts/fetch-raw.sh",
            "line_start": 1,
            "line_end": 1
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.78,
        "confidence_reasoning": "This shell wrapper calls mcp-client.py to run Context7 MCP through npx. That creates an external command and network dependency for each documentation fetch."
      },
      {
        "title": "Unix shell invocation",
        "description": "#!/bin/bash",
        "locations": [
          {
            "file": "scripts/start-server.sh",
            "line_start": 1,
            "line_end": 1
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.75,
        "confidence_reasoning": "This shell script starts an external Context7 MCP server with npx and records PID state. That is expected behavior, but it is a real external command surface."
      },
      {
        "title": "Temp directory access",
        "description": "PID_FILE=\"/tmp/context7-mcp-${PORT}.pid\"",
        "locations": [
          {
            "file": "scripts/start-server.sh",
            "line_start": 6,
            "line_end": 6
          }
        ],
        "review_kind": "capability",
        "source_category": "filesystem",
        "source_severity": "medium",
        "confidence": 0.78,
        "confidence_reasoning": "The script uses a predictable PID file under /tmp derived from the port value. A stale or locally tampered file can influence server lifecycle checks."
      },
      {
        "title": "Shell command substitution",
        "description": "PID=$(cat \"$PID_FILE\")",
        "locations": [
          {
            "file": "scripts/stop-server.sh",
            "line_start": 9,
            "line_end": 9
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.82,
        "confidence_reasoning": "The PID is read from a predictable /tmp file and later used for kill operations. If that file is stale or tampered with, the script can target the wrong process."
      },
      {
        "title": "Unix shell invocation",
        "description": "#!/bin/bash",
        "locations": [
          {
            "file": "scripts/stop-server.sh",
            "line_start": 1,
            "line_end": 1
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.78,
        "confidence_reasoning": "This shell script terminates processes based on a PID file or pkill pattern. Process termination is a real operational risk if inputs or PID state are wrong."
      },
      {
        "title": "Standard device file access",
        "description": "kill \"$PID\" 2>/dev/null",
        "locations": [
          {
            "file": "scripts/stop-server.sh",
            "line_start": 12,
            "line_end": 12
          }
        ],
        "review_kind": "capability",
        "source_category": "filesystem",
        "source_severity": "low",
        "confidence": 0.82,
        "confidence_reasoning": "This sends a signal to the PID read from the predictable /tmp file. If the PID file is stale or tampered with, the wrong process can be terminated."
      },
      {
        "title": "Standard device file access",
        "description": "kill -9 \"$PID\" 2>/dev/null || true",
        "locations": [
          {
            "file": "scripts/stop-server.sh",
            "line_start": 16,
            "line_end": 16
          }
        ],
        "review_kind": "capability",
        "source_category": "filesystem",
        "source_severity": "low",
        "confidence": 0.82,
        "confidence_reasoning": "This force-kills the PID read from the predictable /tmp file. A stale or tampered PID file can cause unintended process termination."
      },
      {
        "title": "Standard device file access",
        "description": "pkill -f \"context7-mcp.*--port.*${PORT}\" 2>/dev/null && echo \"Context7 MCP stopped\" || echo \"Context",
        "locations": [
          {
            "file": "scripts/stop-server.sh",
            "line_start": 25,
            "line_end": 25
          }
        ],
        "review_kind": "capability",
        "source_category": "filesystem",
        "source_severity": "low",
        "confidence": 0.74,
        "confidence_reasoning": "The fallback pkill pattern includes an unvalidated port value. A crafted value can broaden the match against Context7 MCP command lines."
      },
      {
        "title": "Temp directory access",
        "description": "PID_FILE=\"/tmp/context7-mcp-${PORT}.pid\"",
        "locations": [
          {
            "file": "scripts/stop-server.sh",
            "line_start": 6,
            "line_end": 6
          }
        ],
        "review_kind": "capability",
        "source_category": "filesystem",
        "source_severity": "medium",
        "confidence": 0.82,
        "confidence_reasoning": "The predictable /tmp PID path is trusted as process-control state. This can be influenced by stale files or local tampering."
      },
      {
        "title": "Unescaped JSON Parameter Construction",
        "description": "Shell heredocs and inline strings interpolate library, topic, mode, and page values into JSON without json.dumps or another structured encoder. Malformed input can alter or break MCP parameters.",
        "locations": [
          {
            "file": "scripts/fetch-docs.sh",
            "line_start": 93,
            "line_end": 96
          },
          {
            "file": "scripts/fetch-raw.sh",
            "line_start": 13,
            "line_end": 18
          },
          {
            "file": "scripts/fetch-raw.sh",
            "line_start": 23,
            "line_end": 30
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "medium",
        "confidence": 0.78,
        "confidence_reasoning": "The variables are quoted for the shell, so direct command injection is unlikely. They are still inserted into JSON syntax without escaping or type validation."
      },
      {
        "title": "Predictable Temporary PID File Controls Process Termination",
        "description": "The server control scripts use predictable /tmp PID files and then trust those files when checking or killing processes. Stale or locally modified files can affect which process is targeted.",
        "locations": [
          {
            "file": "scripts/start-server.sh",
            "line_start": 6,
            "line_end": 6
          },
          {
            "file": "scripts/stop-server.sh",
            "line_start": 6,
            "line_end": 6
          },
          {
            "file": "scripts/stop-server.sh",
            "line_start": 9,
            "line_end": 16
          },
          {
            "file": "scripts/stop-server.sh",
            "line_start": 25,
            "line_end": 25
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "medium",
        "confidence": 0.82,
        "confidence_reasoning": "The PID file path is deterministic and stored under /tmp, and stop-server.sh sends normal and forced kill signals based on that state. The impact depends on local filesystem access and execution privileges."
      }
    ],
    "low_findings": [
      {
        "title": "HTTP client library",
        "description": "def request(self, method: str, params: Optional[dict] = None) -> dict:",
        "locations": [
          {
            "file": "scripts/mcp-client.py",
            "line_start": 146,
            "line_end": 146
          }
        ],
        "review_kind": "capability",
        "source_category": "network",
        "source_severity": "low",
        "confidence": 0.76,
        "confidence_reasoning": "The client can send JSON-RPC requests to a configured MCP transport, including HTTP URLs. This is expected functionality, but it is real outbound network behavior with request parameters."
      },
      {
        "title": "HTTP client library",
        "description": "result = self.transport.request(\"tools/list\")",
        "locations": [
          {
            "file": "scripts/mcp-client.py",
            "line_start": 314,
            "line_end": 314
          }
        ],
        "review_kind": "capability",
        "source_category": "network",
        "source_severity": "low",
        "confidence": 0.76,
        "confidence_reasoning": "The client can send JSON-RPC requests to a configured MCP transport, including HTTP URLs. This is expected functionality, but it is real outbound network behavior with request parameters."
      },
      {
        "title": "HTTP client library",
        "description": "result = self.transport.request(\"tools/call\", params)",
        "locations": [
          {
            "file": "scripts/mcp-client.py",
            "line_start": 323,
            "line_end": 323
          }
        ],
        "review_kind": "capability",
        "source_category": "network",
        "source_severity": "low",
        "confidence": 0.76,
        "confidence_reasoning": "The client can send JSON-RPC requests to a configured MCP transport, including HTTP URLs. This is expected functionality, but it is real outbound network behavior with request parameters."
      },
      {
        "title": "HTTP client library",
        "description": "result = self.transport.request(\"resources/list\")",
        "locations": [
          {
            "file": "scripts/mcp-client.py",
            "line_start": 328,
            "line_end": 328
          }
        ],
        "review_kind": "capability",
        "source_category": "network",
        "source_severity": "low",
        "confidence": 0.76,
        "confidence_reasoning": "The client can send JSON-RPC requests to a configured MCP transport, including HTTP URLs. This is expected functionality, but it is real outbound network behavior with request parameters."
      },
      {
        "title": "HTTP client library",
        "description": "result = self.transport.request(\"prompts/list\")",
        "locations": [
          {
            "file": "scripts/mcp-client.py",
            "line_start": 333,
            "line_end": 333
          }
        ],
        "review_kind": "capability",
        "source_category": "network",
        "source_severity": "low",
        "confidence": 0.76,
        "confidence_reasoning": "The client can send JSON-RPC requests to a configured MCP transport, including HTTP URLs. This is expected functionality, but it is real outbound network behavior with request parameters."
      },
      {
        "title": "Standard device file access",
        "description": "if kill -0 \"$PID\" 2>/dev/null; then",
        "locations": [
          {
            "file": "scripts/stop-server.sh",
            "line_start": 10,
            "line_end": 10
          }
        ],
        "review_kind": "capability",
        "source_category": "filesystem",
        "source_severity": "low",
        "confidence": 0.68,
        "confidence_reasoning": "This checks a PID loaded from a mutable /tmp file. The check itself is not destructive, but it relies on untrusted process-control state."
      }
    ],
    "dangerous_patterns": [],
    "files_scanned": 10,
    "total_lines": 1333,
    "audit_model": "codex",
    "audited_at": "2026-07-07T18:33:55.247Z",
    "agent_auto_install_policy": "confirmation_required",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Fetch Token-Efficient Context7 Docs",
    "value_statement": "Library documentation often returns too much text for focused coding tasks. This skill fetches Context7 documentation and filters it into concise examples, signatures, and notes.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "Context7 MCP",
      "library documentation",
      "API reference",
      "code examples",
      "token-efficient docs",
      "developer tooling",
      "MCP workflow"
    ],
    "actual_capabilities": [
      "Resolves library names to Context7-compatible library IDs.",
      "Fetches documentation by library ID, topic, mode, and page.",
      "Filters raw documentation into code examples, API signatures, and notes.",
      "Supports code-focused and concept-focused documentation modes.",
      "Provides helper scripts to start and stop a local Context7 MCP server."
    ],
    "limitations": [
      "Requires Bash, Python 3, npx, and network access to Context7 tooling.",
      "Runs an external npm MCP package through shell commands.",
      "Filtering can omit useful context from long documentation pages.",
      "It does not verify returned documentation against project-specific versions."
    ],
    "use_cases": [
      {
        "title": "Look up framework syntax",
        "description": "Fetch concise examples for a specific framework feature without loading full documentation into context.",
        "target_user": "Application developer"
      },
      {
        "title": "Compare API usage patterns",
        "description": "Retrieve signatures and notes for a library before selecting an implementation approach.",
        "target_user": "Technical lead"
      },
      {
        "title": "Support coding assistants",
        "description": "Give Claude, Codex, or Claude Code focused reference material while conserving context window space.",
        "target_user": "AI-assisted engineer"
      }
    ],
    "prompt_templates": [
      {
        "title": "Find basic examples",
        "scenario": "Beginner lookup for a named library feature.",
        "prompt": "Use this skill to fetch concise Context7 examples for React useState."
      },
      {
        "title": "Fetch concept notes",
        "scenario": "Conceptual explanation with fewer code examples.",
        "prompt": "Use info mode to fetch Context7 documentation about Prisma getting started."
      },
      {
        "title": "Use a known library ID",
        "scenario": "Faster lookup when the Context7 library ID is already known.",
        "prompt": "Fetch Context7 docs for /vercel/next.js about routing in code mode."
      },
      {
        "title": "Explore multiple pages",
        "scenario": "Advanced research across paginated documentation results.",
        "prompt": "Fetch page 1 and page 2 of Context7 docs for React hooks, then summarize differences in API examples."
      }
    ],
    "output_examples": [
      {
        "input": "Fetch React hook examples for useState.",
        "output": "A compact result with several React state examples, related function signatures, and important usage notes."
      },
      {
        "input": "Fetch conceptual documentation for Prisma getting started.",
        "output": "A short overview with selected examples and notes about setup steps and common workflow choices."
      },
      {
        "input": "Fetch Next.js routing documentation by known Context7 library ID.",
        "output": "Focused routing reference material with examples and key notes instead of the full raw documentation response."
      }
    ],
    "best_practices": [
      "Prefer a specific topic so the filter returns relevant examples.",
      "Use a known Context7 library ID when accuracy matters.",
      "Review filtered output against official documentation before making production changes."
    ],
    "anti_patterns": [
      "Do not use this skill for offline or confidential documentation workflows.",
      "Do not pass untrusted shell values into helper scripts without review.",
      "Do not assume filtered snippets include every required setup step."
    ],
    "faq": [
      {
        "question": "What does this skill fetch?",
        "answer": "It fetches library documentation from Context7 and filters it into shorter reference output."
      },
      {
        "question": "Does it work without network access?",
        "answer": "No. It depends on Context7 MCP tooling and npx package execution."
      },
      {
        "question": "Can I use it with Claude Code?",
        "answer": "Yes. The report lists compatibility with Claude, Codex, and Claude Code."
      },
      {
        "question": "Why does it use shell scripts?",
        "answer": "The scripts keep large raw documentation responses outside the assistant context and return filtered text."
      },
      {
        "question": "Does it validate documentation versions?",
        "answer": "No. It requests Context7 documentation but does not verify version alignment with a local project."
      },
      {
        "question": "What should users review before installing?",
        "answer": "Users should review the shell scripts, npx package execution, network behavior, and MCP client command handling."
      }
    ]
  },
  "file_structure": [
    {
      "name": "references",
      "type": "dir",
      "path": "references",
      "children": [
        {
          "name": "context7-tools.md",
          "type": "file",
          "path": "references/context7-tools.md",
          "lines": 226
        }
      ]
    },
    {
      "name": "scripts",
      "type": "dir",
      "path": "scripts",
      "children": [
        {
          "name": "extract-code-blocks.sh",
          "type": "file",
          "path": "scripts/extract-code-blocks.sh",
          "lines": 57
        },
        {
          "name": "extract-notes.sh",
          "type": "file",
          "path": "scripts/extract-notes.sh",
          "lines": 13
        },
        {
          "name": "extract-signatures.sh",
          "type": "file",
          "path": "scripts/extract-signatures.sh",
          "lines": 43
        },
        {
          "name": "fetch-docs.sh",
          "type": "file",
          "path": "scripts/fetch-docs.sh",
          "lines": 208
        },
        {
          "name": "fetch-raw.sh",
          "type": "file",
          "path": "scripts/fetch-raw.sh",
          "lines": 39
        },
        {
          "name": "mcp-client.py",
          "type": "file",
          "path": "scripts/mcp-client.py",
          "lines": 491
        },
        {
          "name": "start-server.sh",
          "type": "file",
          "path": "scripts/start-server.sh",
          "lines": 27
        },
        {
          "name": "stop-server.sh",
          "type": "file",
          "path": "scripts/stop-server.sh",
          "lines": 27
        }
      ]
    },
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 202
    }
  ]
}
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall