Skip to content

aiskillstore/marketplace / skills/101-skills/web-search

web-search

Verified

Web search and content extraction with Tavily and Exa via inference.sh CLI. Apps: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. Capabilities: AI-powered search, content extraction, direct answers, research. Use for: research, RAG pipelines, fact-checking, content aggregation, agents. Triggers: web search, tavily, exa, search api, content extraction, research, internet search, ai search, search assistant, web scraping, rag, perplexity alternative

FileKindSize
SKILL.mdskill md4.0 KB
skill-report.jsonconfig42.3 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-12T10:27:09.575Z",
    "slug": "101-skills-web-search",
    "source_url": "https://github.com/101-skills/skills/tree/main/tools/llm/web-search/",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "22a0ec550a3d0e13caf251d6a0d08c81cb387b7ec4af98c194299393101cf5b9",
    "tree_hash": "2bf7bddaf9e10d180db80bbcb2c96514b18e90bbbee41a90b8f361ff81375c36",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "web-search",
    "description": "Search the web, extract page content, generate sourced answers, and combine Tavily or Exa results with language models through the belt CLI.",
    "summary": "Run Tavily and Exa search and extraction workflows through the belt CLI.",
    "icon": "📦",
    "version": "1.0.2",
    "author": "101-skills",
    "license": "MIT",
    "category": "research",
    "tags": [
      "web-search",
      "tavily",
      "exa",
      "content-extraction",
      "rag"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands",
      "network"
    ]
  },
  "security_audit": {
    "risk_level": "medium",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "The skill intentionally runs belt and npx commands, including third-party installation and remote search requests. Most static alerts are Markdown formatting, while several command blocks and one remote image are genuine security surfaces. The workflows also disclose inputs externally and may pass untrusted web content into language models.",
    "remediation": [
      {
        "issue": "The installation examples execute third-party packages without a pinned version.",
        "suggestion": "Pin package and skill versions, publish integrity information, and require user confirmation before installation.",
        "severity": "medium"
      },
      {
        "issue": "Search queries, questions, URLs, and extracted content are sent to external providers.",
        "suggestion": "Document each provider and warn users not to submit secrets, personal data, or private URLs.",
        "severity": "medium"
      },
      {
        "issue": "Retrieved web content may contain instructions designed to manipulate a language model.",
        "suggestion": "Tell agents to treat retrieved text as untrusted data and never follow instructions embedded in source content.",
        "severity": "medium"
      },
      {
        "issue": "The documentation embeds an image from an external host.",
        "suggestion": "Bundle the image with the skill or use a trusted marketplace proxy to prevent viewer tracking.",
        "severity": "low"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 7,
            "line_end": 7
          },
          {
            "file": "SKILL.md",
            "line_start": 17,
            "line_end": 17
          },
          {
            "file": "SKILL.md",
            "line_start": 19,
            "line_end": 24
          },
          {
            "file": "SKILL.md",
            "line_start": 24,
            "line_end": 33
          },
          {
            "file": "SKILL.md",
            "line_start": 33,
            "line_end": 34
          },
          {
            "file": "SKILL.md",
            "line_start": 34,
            "line_end": 40
          },
          {
            "file": "SKILL.md",
            "line_start": 40,
            "line_end": 41
          },
          {
            "file": "SKILL.md",
            "line_start": 41,
            "line_end": 42
          },
          {
            "file": "SKILL.md",
            "line_start": 42,
            "line_end": 48
          },
          {
            "file": "SKILL.md",
            "line_start": 48,
            "line_end": 52
          },
          {
            "file": "SKILL.md",
            "line_start": 52,
            "line_end": 58
          },
          {
            "file": "SKILL.md",
            "line_start": 58,
            "line_end": 62
          },
          {
            "file": "SKILL.md",
            "line_start": 62,
            "line_end": 68
          },
          {
            "file": "SKILL.md",
            "line_start": 68,
            "line_end": 72
          },
          {
            "file": "SKILL.md",
            "line_start": 72,
            "line_end": 78
          },
          {
            "file": "SKILL.md",
            "line_start": 78,
            "line_end": 82
          },
          {
            "file": "SKILL.md",
            "line_start": 82,
            "line_end": 88
          },
          {
            "file": "SKILL.md",
            "line_start": 88,
            "line_end": 92
          },
          {
            "file": "SKILL.md",
            "line_start": 92,
            "line_end": 98
          },
          {
            "file": "SKILL.md",
            "line_start": 98,
            "line_end": 108
          },
          {
            "file": "SKILL.md",
            "line_start": 108,
            "line_end": 112
          },
          {
            "file": "SKILL.md",
            "line_start": 112,
            "line_end": 122
          },
          {
            "file": "SKILL.md",
            "line_start": 122,
            "line_end": 134
          },
          {
            "file": "SKILL.md",
            "line_start": 134,
            "line_end": 143
          },
          {
            "file": "SKILL.md",
            "line_start": 143,
            "line_end": 145
          }
        ]
      },
      {
        "factor": "network",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 11,
            "line_end": 11
          },
          {
            "file": "SKILL.md",
            "line_start": 13,
            "line_end": 13
          },
          {
            "file": "SKILL.md",
            "line_start": 17,
            "line_end": 17
          },
          {
            "file": "SKILL.md",
            "line_start": 60,
            "line_end": 60
          },
          {
            "file": "SKILL.md",
            "line_start": 90,
            "line_end": 90
          },
          {
            "file": "SKILL.md",
            "line_start": 115,
            "line_end": 115
          },
          {
            "file": "SKILL.md",
            "line_start": 149,
            "line_end": 149
          },
          {
            "file": "SKILL.md",
            "line_start": 150,
            "line_end": 150
          },
          {
            "file": "SKILL.md",
            "line_start": 151,
            "line_end": 151
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:7:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 7,
        "line_end": 7,
        "snippet": "> **Install the belt CLI skill:** `npx skills add belt-sh/cli`"
      },
      {
        "id": "external_commands:SKILL.md:17:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 17,
        "line_end": 17,
        "snippet": "> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/infer"
      },
      {
        "id": "external_commands:SKILL.md:19:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 19,
        "line_end": 24,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 24,
        "line_end": 33,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:33:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 33,
        "line_end": 34,
        "snippet": "| Search Assistant | `tavily/search-assistant` | AI-powered search with answers |"
      },
      {
        "id": "external_commands:SKILL.md:34:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 34,
        "line_end": 40,
        "snippet": "| Extract | `tavily/extract` | Extract content from URLs |"
      },
      {
        "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": 41,
        "snippet": "| Search | `exa/search` | Smart web search with AI |"
      },
      {
        "id": "external_commands:SKILL.md:41:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 41,
        "line_end": 42,
        "snippet": "| Answer | `exa/answer` | Direct factual answers |"
      },
      {
        "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": 48,
        "snippet": "| Extract | `exa/extract` | Extract and analyze web content |"
      },
      {
        "id": "external_commands:SKILL.md:48:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 48,
        "line_end": 52,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:52:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 52,
        "line_end": 58,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 58,
        "line_end": 62,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:62:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 62,
        "line_end": 68,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 68,
        "line_end": 72,
        "snippet": "```bash"
      },
      {
        "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": 78,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:78:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 78,
        "line_end": 82,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:82:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 82,
        "line_end": 88,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:88:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 88,
        "line_end": 92,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:92:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 92,
        "line_end": 98,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:98:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 98,
        "line_end": 108,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:108:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 108,
        "line_end": 112,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:112:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 112,
        "line_end": 122,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:122:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 122,
        "line_end": 134,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:134:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 134,
        "line_end": 143,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:143:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 143,
        "line_end": 145,
        "snippet": "```"
      },
      {
        "id": "network:SKILL.md:11:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 11,
        "line_end": 11,
        "snippet": "Search the web and extract content via [inference.sh](https://inference.sh) CLI."
      },
      {
        "id": "network:SKILL.md:13:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 13,
        "line_end": 13,
        "snippet": "![Web Search & Extraction](https://cloud.inference.sh/app/files/u/4mg21r6ta37mpaz6ktzwtt8krr/01kgndq"
      },
      {
        "id": "network:SKILL.md:17:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 17,
        "line_end": 17,
        "snippet": "> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/infer"
      },
      {
        "id": "network:SKILL.md:60:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 60,
        "line_end": 60,
        "snippet": "\"urls\": [\"https://example.com/article1\", \"https://example.com/article2\"]"
      },
      {
        "id": "network:SKILL.md:90:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 90,
        "line_end": 90,
        "snippet": "\"url\": \"https://example.com/research-paper\""
      },
      {
        "id": "network:SKILL.md:115:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 115,
        "line_end": 115,
        "snippet": "\"urls\": [\"https://example.com/long-article\"]"
      },
      {
        "id": "network:SKILL.md:149:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 149,
        "line_end": 149,
        "snippet": "- [Adding Tools to Agents](https://inference.sh/docs/agents/adding-tools) - Equip agents with search"
      },
      {
        "id": "network:SKILL.md:150:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 150,
        "line_end": 150,
        "snippet": "- [Building a Research Agent](https://inference.sh/blog/guides/research-agent) - LLM + search integr"
      },
      {
        "id": "network:SKILL.md:151:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 151,
        "line_end": 151,
        "snippet": "- [Tool Integration Tax](https://inference.sh/blog/tools/integration-tax) - Why pre-built tools matt"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:7:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.98,
        "reason": "Line 7 instructs users to execute npx and install a third-party skill, creating package and supply-chain exposure.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:17:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks on line 17 only format the belt executable name in prose and do not execute a command."
      },
      {
        "id": "external_commands:SKILL.md:19:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.99,
        "reason": "Lines 19 through 24 run belt login and a remote Tavily app, which are intentional external command executions.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "This range contains a closing code fence and formatted application identifiers, not a shell command."
      },
      {
        "id": "external_commands:SKILL.md:33:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks format a Tavily application identifier inside a Markdown table and do not invoke a shell."
      },
      {
        "id": "external_commands:SKILL.md:34:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The range contains formatted Tavily and Exa application identifiers, with no executable shell expression."
      },
      {
        "id": "external_commands:SKILL.md:40:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks only identify the exa/search application in a table."
      },
      {
        "id": "external_commands:SKILL.md:41:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks only identify the exa/answer application in a table."
      },
      {
        "id": "external_commands:SKILL.md:42:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The range formats an application identifier and opens an example block, but contains no command invocation."
      },
      {
        "id": "external_commands:SKILL.md:48:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.99,
        "reason": "Lines 48 through 52 execute belt app run to send a query to the Tavily search service.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:52:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "This range contains code-fence delimiters and descriptive text, not an executed command."
      },
      {
        "id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.99,
        "reason": "Lines 58 through 62 execute belt app run and submit URLs to Tavily for extraction.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:62:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "This range closes one example and opens another without containing a shell command."
      },
      {
        "id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.99,
        "reason": "Lines 68 through 72 execute belt app run and send a search query to Exa.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:72:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "This range contains Markdown boundaries and explanatory text, with no command invocation."
      },
      {
        "id": "external_commands:SKILL.md:78:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.99,
        "reason": "Lines 78 through 82 execute belt app run and send a factual question to Exa.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:82:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "This range contains Markdown boundaries and prose, not executable shell content."
      },
      {
        "id": "external_commands:SKILL.md:88:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.99,
        "reason": "Lines 88 through 92 execute belt app run and submit a URL to Exa for extraction.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:92:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "This range closes the extraction example and opens a workflow block without running a command."
      },
      {
        "id": "external_commands:SKILL.md:98:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.99,
        "reason": "Lines 98 through 108 run Tavily and OpenRouter commands and redirect search output into a local file.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:108:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "This range contains a closing fence, a heading, and an opening fence, but no command."
      },
      {
        "id": "external_commands:SKILL.md:112:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.99,
        "reason": "Lines 112 through 122 run Tavily and OpenRouter commands and redirect extracted content into a local file.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:122:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "This range contains a closing fence, use-case prose, and an opening fence without an actual command."
      },
      {
        "id": "external_commands:SKILL.md:134:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.99,
        "reason": "Lines 134 through 143 execute three npx installation commands for external skills without pinned versions.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:143:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.96,
        "reason": "The finding range includes the instruction to run belt app store, which invokes an external CLI.",
        "severity": "medium"
      },
      {
        "id": "network:SKILL.md:11:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Line 11 is a normal documentation link to the named service and does not automatically send data."
      },
      {
        "id": "network:SKILL.md:13:hardcoded-url",
        "verdict": "confirmed",
        "confidence": 0.92,
        "reason": "Line 13 embeds a remotely hosted image, allowing the host to observe requests from documentation viewers.",
        "severity": "low"
      },
      {
        "id": "network:SKILL.md:17:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.9,
        "reason": "Line 17 is a visible link to public installation documentation and does not fetch or execute it automatically."
      },
      {
        "id": "network:SKILL.md:60:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The URLs use the reserved example.com domain as placeholders for an extraction example."
      },
      {
        "id": "network:SKILL.md:90:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The URL uses the reserved example.com domain as a placeholder and does not identify a real destination."
      },
      {
        "id": "network:SKILL.md:115:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The URL uses the reserved example.com domain as a placeholder for a documented workflow."
      },
      {
        "id": "network:SKILL.md:149:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Line 149 is a standard documentation link to the skill provider and does not create an automatic request."
      },
      {
        "id": "network:SKILL.md:150:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Line 150 is a standard guide link to the skill provider and does not create an automatic request."
      },
      {
        "id": "network:SKILL.md:151:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Line 151 is a standard article link to the skill provider and does not create an automatic request."
      }
    ],
    "semantic_findings": [
      {
        "title": "User Data Sent to External Search Providers",
        "description": "The examples send user queries, questions, and target URLs through belt to Tavily, Exa, and inference.sh services.",
        "severity": "medium",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 48,
            "line_end": 91
          }
        ],
        "confidence": 0.97,
        "confidence_reasoning": "The documented commands explicitly place queries, questions, and URLs in inputs for remote provider applications."
      },
      {
        "title": "Untrusted Web Content Used in LLM Workflows",
        "description": "The workflows recommend summarizing retrieved web material without guidance for resisting instructions embedded in that material.",
        "severity": "medium",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 96,
            "line_end": 121
          }
        ],
        "confidence": 0.82,
        "confidence_reasoning": "The examples combine search or extraction with LLM prompts, although placeholders prevent fully automatic data flow."
      }
    ],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [
      {
        "title": "Ruby/shell backtick execution",
        "description": "> **Install the belt CLI skill:** `npx skills add belt-sh/cli`",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 7,
            "line_end": 7
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.98,
        "confidence_reasoning": "Line 7 instructs users to execute npx and install a third-party skill, creating package and supply-chain exposure."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 19,
            "line_end": 24
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.99,
        "confidence_reasoning": "Lines 19 through 24 run belt login and a remote Tavily app, which are intentional external command executions."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 48,
            "line_end": 52
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.99,
        "confidence_reasoning": "Lines 48 through 52 execute belt app run to send a query to the Tavily search service."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 58,
            "line_end": 62
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.99,
        "confidence_reasoning": "Lines 58 through 62 execute belt app run and submit URLs to Tavily for extraction."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 68,
            "line_end": 72
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.99,
        "confidence_reasoning": "Lines 68 through 72 execute belt app run and send a search query to Exa."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 78,
            "line_end": 82
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.99,
        "confidence_reasoning": "Lines 78 through 82 execute belt app run and send a factual question to Exa."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 88,
            "line_end": 92
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.99,
        "confidence_reasoning": "Lines 88 through 92 execute belt app run and submit a URL to Exa for extraction."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 98,
            "line_end": 108
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.99,
        "confidence_reasoning": "Lines 98 through 108 run Tavily and OpenRouter commands and redirect search output into a local file."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 112,
            "line_end": 122
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.99,
        "confidence_reasoning": "Lines 112 through 122 run Tavily and OpenRouter commands and redirect extracted content into a local file."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 134,
            "line_end": 143
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.99,
        "confidence_reasoning": "Lines 134 through 143 execute three npx installation commands for external skills without pinned versions."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 143,
            "line_end": 145
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.96,
        "confidence_reasoning": "The finding range includes the instruction to run belt app store, which invokes an external CLI."
      },
      {
        "title": "User Data Sent to External Search Providers",
        "description": "The examples send user queries, questions, and target URLs through belt to Tavily, Exa, and inference.sh services.",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 48,
            "line_end": 91
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "medium",
        "confidence": 0.97,
        "confidence_reasoning": "The documented commands explicitly place queries, questions, and URLs in inputs for remote provider applications."
      },
      {
        "title": "Untrusted Web Content Used in LLM Workflows",
        "description": "The workflows recommend summarizing retrieved web material without guidance for resisting instructions embedded in that material.",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 96,
            "line_end": 121
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "medium",
        "confidence": 0.82,
        "confidence_reasoning": "The examples combine search or extraction with LLM prompts, although placeholders prevent fully automatic data flow."
      }
    ],
    "low_findings": [
      {
        "title": "Hardcoded URL",
        "description": "![Web Search & Extraction](https://cloud.inference.sh/app/files/u/4mg21r6ta37mpaz6ktzwtt8krr/01kgndq",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 13,
            "line_end": 13
          }
        ],
        "review_kind": "capability",
        "source_category": "network",
        "source_severity": "low",
        "confidence": 0.92,
        "confidence_reasoning": "Line 13 embeds a remotely hosted image, allowing the host to observe requests from documentation viewers."
      }
    ],
    "dangerous_patterns": [],
    "files_scanned": 1,
    "total_lines": 153,
    "audit_model": "codex",
    "audited_at": "2026-07-12T10:27:09.575Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Search and Extract Web Research",
    "value_statement": "Current information is difficult to gather and normalize across sources. This skill uses Tavily and Exa to search, answer questions, and extract web content.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "web search skill",
      "Tavily search",
      "Exa search",
      "web content extraction",
      "AI research assistant",
      "RAG research"
    ],
    "actual_capabilities": [
      "Searches the web with Tavily Search Assistant.",
      "Finds relevant links and context with Exa Search.",
      "Returns direct factual answers through Exa Answer.",
      "Extracts text and images from one or more public URLs.",
      "Combines retrieved material with supported language models for summaries."
    ],
    "limitations": [
      "Requires the belt CLI, an inference.sh account, and network access.",
      "Search quality and availability depend on Tavily, Exa, and inference.sh.",
      "Queries, questions, and URLs are sent to external service providers.",
      "Does not guarantee source accuracy or access to restricted pages."
    ],
    "use_cases": [
      {
        "title": "Investigate Current Topics",
        "description": "Collect recent sources, concise summaries, and links for a focused research question.",
        "target_user": "Researchers and analysts"
      },
      {
        "title": "Verify Published Claims",
        "description": "Find independent sources that support, contradict, or qualify a claim before publication.",
        "target_user": "Editors and fact-checkers"
      },
      {
        "title": "Prepare RAG Source Material",
        "description": "Discover and extract public pages for review before adding them to a retrieval pipeline.",
        "target_user": "AI application developers"
      }
    ],
    "prompt_templates": [
      {
        "title": "Find Sources",
        "prompt": "Search the web for [topic]. Return five relevant sources with titles, dates, links, and one-sentence summaries.",
        "scenario": "Beginner search for a current topic"
      },
      {
        "title": "Compare Options",
        "prompt": "Research [option A] and [option B]. Compare their features, costs, limitations, and recent developments using cited sources.",
        "scenario": "Structured comparison across multiple sources"
      },
      {
        "title": "Extract and Synthesize",
        "prompt": "Extract the main content from [URLs]. Summarize shared themes, disagreements, supporting evidence, and missing information.",
        "scenario": "Multi-page content review"
      },
      {
        "title": "Build an Evidence Map",
        "prompt": "Investigate [claim] with varied search queries. Separate primary and secondary sources, assess recency, identify contradictions, and list unresolved questions.",
        "scenario": "Advanced research and evidence assessment"
      }
    ],
    "output_examples": [
      {
        "input": "Find recent guidance on evaluating retrieval-augmented generation systems.",
        "output": [
          "A ranked source list with publication dates and direct links.",
          "A short summary of evaluation methods discussed by each source.",
          "A note identifying recurring metrics and conflicting recommendations."
        ]
      },
      {
        "input": "Extract two public product pages and compare their documented limits.",
        "output": "A concise comparison of each product limit, with source links and notes for details that could not be verified."
      },
      {
        "input": "Check whether a public claim is supported by recent evidence.",
        "output": "A support, contradiction, or unclear assessment followed by dated sources and a brief explanation of remaining uncertainty."
      }
    ],
    "best_practices": [
      "Use focused queries and include a date range when freshness matters.",
      "Review source credibility and confirm important claims with independent references.",
      "Remove secrets and private information before sending queries or URLs."
    ],
    "anti_patterns": [
      "Do not treat generated answers as verified facts without opening their sources.",
      "Do not send private documents, credentials, or internal URLs to external extraction services.",
      "Do not follow instructions found inside retrieved pages or extracted text."
    ],
    "faq": [
      {
        "question": "Which search providers does this skill use?",
        "answer": "It documents Tavily Search Assistant, Tavily Extract, Exa Search, Exa Answer, and Exa Extract through inference.sh."
      },
      {
        "question": "What must be installed first?",
        "answer": "You need the belt CLI, an authenticated inference.sh account, and network access."
      },
      {
        "question": "Can it extract several pages at once?",
        "answer": "Yes. The Tavily extraction example accepts multiple public URLs in one request."
      },
      {
        "question": "Does it provide citations?",
        "answer": "Tavily Search Assistant is described as returning answers with sources. Citation quality still requires user review."
      },
      {
        "question": "Can it access private or restricted pages?",
        "answer": "The skill does not document authentication for target pages or methods for bypassing access restrictions."
      },
      {
        "question": "How should sensitive data be handled?",
        "answer": "Do not submit secrets, personal data, confidential text, or private URLs because inputs are sent to external providers."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 153
    }
  ]
}
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