Skip to content

aiskillstore/marketplace / skills/2389-research/binary-re-dynamic-analysis

binary-re-dynamic-analysis

Verified

Use when you need to run a binary, trace execution, or observe runtime behavior. Runtime analysis via QEMU emulation, GDB debugging, and Frida hooking - syscall tracing (strace), breakpoints, memory inspection, function interception. Keywords - "run binary", "execute", "debug", "trace syscalls", "set breakpoint", "qemu", "gdb", "frida", "strace", "watch memory"

FileKindSize
SKILL.mdskill md14.6 KB
skill-report.jsonconfig111.4 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-09T01:41:28.477Z",
    "slug": "2389-research-binary-re-dynamic-analysis",
    "source_url": "https://github.com/2389-research/claude-plugins/tree/main/binary-re/skills/dynamic-analysis",
    "source_ref": "main",
    "model": "claude",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "ade40608679c066ff4102ff9d4c34d02e3fa07d6d3aa9c268c0d3ecb95f141ca",
    "tree_hash": "8bb9ca2baa55b69394ba0b3f3b2e5d7aaf2842baec68f69eaa5c6b48ad7bd98c",
    "provenance": {
      "model_requested": "claude-sonnet-4.6",
      "model_effective": "claude:claude-sonnet-4.6",
      "fallback_chain": [
        {
          "agent": "claude",
          "model": "claude-sonnet-4.6",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "binary-re-dynamic-analysis",
    "description": "Guide Claude, Codex, or Claude Code through dynamic binary analysis with QEMU, GDB, Frida, Docker, and syscall tracing. It emphasizes human approval, sandbox configuration, runtime observation, and structured evidence capture.",
    "summary": "Run and observe binaries safely with QEMU, GDB, Frida, Docker, and syscall tracing workflows.",
    "icon": "📦",
    "version": "1.0.0",
    "author": "2389-research",
    "license": "MIT",
    "tags": [
      "binary-analysis",
      "reverse-engineering",
      "dynamic-analysis",
      "debugging",
      "sandboxing"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands",
      "network",
      "filesystem"
    ],
    "category": "security"
  },
  "security_audit": {
    "risk_level": "critical",
    "is_blocked": true,
    "safe_to_publish": false,
    "analysis_status": "ok",
    "summary": "The skill is primarily an authorized dynamic binary analysis guide and includes an explicit human-approval requirement. Confirmed risks remain because it instructs users to execute unknown binaries, use privileged Docker for binfmt setup, source local GDB configuration, create linker symlinks, and optionally run samples on low-isolation devices.",
    "remediation": [
      {
        "issue": "Privileged Docker setup for binfmt registration",
        "suggestion": "Move privileged setup into an optional, clearly separated administrator step and provide non-privileged alternatives where possible.",
        "severity": "critical"
      },
      {
        "issue": "Unknown binary execution workflows",
        "suggestion": "Add stronger defaults for network blocking, read-only mounts, non-root users, timeouts, and disposable sandboxes before each execution example.",
        "severity": "high"
      },
      {
        "issue": "On-device analysis has low isolation",
        "suggestion": "Require dedicated sacrificial devices or lab networks for on-device execution and warn against using production or personal devices.",
        "severity": "high"
      },
      {
        "issue": "GDB configuration and symlink examples can execute or modify local state",
        "suggestion": "Warn that sourced debugger files and linker symlink changes are executable or state-changing, and constrain them to trusted files or containers.",
        "severity": "medium"
      },
      {
        "issue": "Anti-analysis bypass guidance is dual-use",
        "suggestion": "Add an explicit authorization statement before bypass techniques and limit examples to owned, lab, CTF, or incident-response contexts.",
        "severity": "medium"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 26,
            "line_end": 26
          },
          {
            "file": "SKILL.md",
            "line_start": 27,
            "line_end": 27
          },
          {
            "file": "SKILL.md",
            "line_start": 29,
            "line_end": 29
          },
          {
            "file": "SKILL.md",
            "line_start": 34,
            "line_end": 41
          },
          {
            "file": "SKILL.md",
            "line_start": 41,
            "line_end": 45
          },
          {
            "file": "SKILL.md",
            "line_start": 45,
            "line_end": 47
          },
          {
            "file": "SKILL.md",
            "line_start": 47,
            "line_end": 53
          },
          {
            "file": "SKILL.md",
            "line_start": 53,
            "line_end": 73
          },
          {
            "file": "SKILL.md",
            "line_start": 73,
            "line_end": 82
          },
          {
            "file": "SKILL.md",
            "line_start": 82,
            "line_end": 88
          },
          {
            "file": "SKILL.md",
            "line_start": 88,
            "line_end": 88
          },
          {
            "file": "SKILL.md",
            "line_start": 89,
            "line_end": 89
          },
          {
            "file": "SKILL.md",
            "line_start": 90,
            "line_end": 90
          },
          {
            "file": "SKILL.md",
            "line_start": 91,
            "line_end": 95
          },
          {
            "file": "SKILL.md",
            "line_start": 95,
            "line_end": 107
          },
          {
            "file": "SKILL.md",
            "line_start": 107,
            "line_end": 113
          },
          {
            "file": "SKILL.md",
            "line_start": 113,
            "line_end": 128
          },
          {
            "file": "SKILL.md",
            "line_start": 128,
            "line_end": 136
          },
          {
            "file": "SKILL.md",
            "line_start": 136,
            "line_end": 146
          },
          {
            "file": "SKILL.md",
            "line_start": 146,
            "line_end": 150
          },
          {
            "file": "SKILL.md",
            "line_start": 150,
            "line_end": 171
          },
          {
            "file": "SKILL.md",
            "line_start": 171,
            "line_end": 177
          },
          {
            "file": "SKILL.md",
            "line_start": 177,
            "line_end": 183
          },
          {
            "file": "SKILL.md",
            "line_start": 183,
            "line_end": 187
          },
          {
            "file": "SKILL.md",
            "line_start": 187,
            "line_end": 202
          },
          {
            "file": "SKILL.md",
            "line_start": 202,
            "line_end": 217
          },
          {
            "file": "SKILL.md",
            "line_start": 217,
            "line_end": 218
          },
          {
            "file": "SKILL.md",
            "line_start": 218,
            "line_end": 224
          },
          {
            "file": "SKILL.md",
            "line_start": 224,
            "line_end": 228
          },
          {
            "file": "SKILL.md",
            "line_start": 228,
            "line_end": 246
          },
          {
            "file": "SKILL.md",
            "line_start": 246,
            "line_end": 248
          },
          {
            "file": "SKILL.md",
            "line_start": 248,
            "line_end": 251
          },
          {
            "file": "SKILL.md",
            "line_start": 251,
            "line_end": 255
          },
          {
            "file": "SKILL.md",
            "line_start": 255,
            "line_end": 269
          },
          {
            "file": "SKILL.md",
            "line_start": 269,
            "line_end": 273
          },
          {
            "file": "SKILL.md",
            "line_start": 273,
            "line_end": 281
          },
          {
            "file": "SKILL.md",
            "line_start": 281,
            "line_end": 289
          },
          {
            "file": "SKILL.md",
            "line_start": 289,
            "line_end": 303
          },
          {
            "file": "SKILL.md",
            "line_start": 303,
            "line_end": 307
          },
          {
            "file": "SKILL.md",
            "line_start": 307,
            "line_end": 312
          },
          {
            "file": "SKILL.md",
            "line_start": 312,
            "line_end": 316
          },
          {
            "file": "SKILL.md",
            "line_start": 316,
            "line_end": 321
          },
          {
            "file": "SKILL.md",
            "line_start": 321,
            "line_end": 327
          },
          {
            "file": "SKILL.md",
            "line_start": 327,
            "line_end": 329
          },
          {
            "file": "SKILL.md",
            "line_start": 329,
            "line_end": 333
          },
          {
            "file": "SKILL.md",
            "line_start": 333,
            "line_end": 339
          },
          {
            "file": "SKILL.md",
            "line_start": 339,
            "line_end": 349
          },
          {
            "file": "SKILL.md",
            "line_start": 349,
            "line_end": 358
          },
          {
            "file": "SKILL.md",
            "line_start": 358,
            "line_end": 362
          },
          {
            "file": "SKILL.md",
            "line_start": 362,
            "line_end": 368
          }
        ]
      },
      {
        "factor": "network",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 480,
            "line_end": 480
          },
          {
            "file": "SKILL.md",
            "line_start": 493,
            "line_end": 493
          },
          {
            "file": "SKILL.md",
            "line_start": 541,
            "line_end": 541
          },
          {
            "file": "SKILL.md",
            "line_start": 555,
            "line_end": 555
          }
        ]
      },
      {
        "factor": "filesystem",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 144,
            "line_end": 144
          },
          {
            "file": "SKILL.md",
            "line_start": 144,
            "line_end": 144
          },
          {
            "file": "SKILL.md",
            "line_start": 404,
            "line_end": 404
          },
          {
            "file": "SKILL.md",
            "line_start": 413,
            "line_end": 413
          },
          {
            "file": "SKILL.md",
            "line_start": 420,
            "line_end": 420
          },
          {
            "file": "SKILL.md",
            "line_start": 428,
            "line_end": 428
          },
          {
            "file": "SKILL.md",
            "line_start": 295,
            "line_end": 295
          },
          {
            "file": "SKILL.md",
            "line_start": 298,
            "line_end": 298
          },
          {
            "file": "SKILL.md",
            "line_start": 52,
            "line_end": 52
          },
          {
            "file": "SKILL.md",
            "line_start": 170,
            "line_end": 170
          },
          {
            "file": "SKILL.md",
            "line_start": 364,
            "line_end": 364
          },
          {
            "file": "SKILL.md",
            "line_start": 367,
            "line_end": 367
          },
          {
            "file": "SKILL.md",
            "line_start": 448,
            "line_end": 448
          },
          {
            "file": "SKILL.md",
            "line_start": 295,
            "line_end": 295
          },
          {
            "file": "SKILL.md",
            "line_start": 178,
            "line_end": 178
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 26,
        "line_end": 26,
        "snippet": "| Linux x86_64 | ARM32/64, MIPS | Native `qemu-user` | Low |"
      },
      {
        "id": "external_commands:SKILL.md:27:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 27,
        "line_end": 27,
        "snippet": "| Linux x86_64 | x86-32 | Native or `linux32` | Low |"
      },
      {
        "id": "external_commands:SKILL.md:29:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 29,
        "line_end": 29,
        "snippet": "| macOS (any) | x86-32 | Docker `--platform linux/i386` | Medium |"
      },
      {
        "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": 41,
        "snippet": "```bash"
      },
      {
        "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": 45,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:45:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 45,
        "line_end": 47,
        "snippet": "**CRITICAL:** On Colima, `/tmp` mounts often fail silently. Always use home directory paths:"
      },
      {
        "id": "external_commands:SKILL.md:47:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 47,
        "line_end": 53,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:53:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 53,
        "line_end": 73,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:73:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 73,
        "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": 88,
        "snippet": "| ARM glibc hard-float | `/usr/arm-linux-gnueabihf` | `-L` |"
      },
      {
        "id": "external_commands:SKILL.md:89:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 89,
        "line_end": 89,
        "snippet": "| ARM glibc soft-float | `/usr/arm-linux-gnueabi` | `-L` |"
      },
      {
        "id": "external_commands:SKILL.md:90:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 90,
        "line_end": 90,
        "snippet": "| ARM64 glibc | `/usr/aarch64-linux-gnu` | `-L` |"
      },
      {
        "id": "external_commands:SKILL.md:91:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 91,
        "line_end": 95,
        "snippet": "| ARM musl | Custom extraction needed | `-L` |"
      },
      {
        "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": 107,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:107:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 107,
        "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": 128,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:128:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 128,
        "line_end": 136,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:136:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 136,
        "line_end": 146,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:146:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 146,
        "line_end": 150,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:150:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 150,
        "line_end": 171,
        "snippet": "```gdb"
      },
      {
        "id": "external_commands:SKILL.md:171:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 171,
        "line_end": 177,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:177:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 177,
        "line_end": 183,
        "snippet": "```gdb"
      },
      {
        "id": "external_commands:SKILL.md:183:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 183,
        "line_end": 187,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:187:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 187,
        "line_end": 202,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:202:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 202,
        "line_end": 217,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:217:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 217,
        "line_end": 218,
        "snippet": "For cross-arch Frida, deploy `frida-server` to the target device:"
      },
      {
        "id": "external_commands:SKILL.md:218:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 218,
        "line_end": 224,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:224:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 224,
        "line_end": 228,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:228:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 228,
        "line_end": 246,
        "snippet": "```javascript"
      },
      {
        "id": "external_commands:SKILL.md:246:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 246,
        "line_end": 248,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:248:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 248,
        "line_end": 251,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:251:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 251,
        "line_end": 255,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:255:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 255,
        "line_end": 269,
        "snippet": "```javascript"
      },
      {
        "id": "external_commands:SKILL.md:269:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 269,
        "line_end": 273,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:273:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 273,
        "line_end": 281,
        "snippet": "```javascript"
      },
      {
        "id": "external_commands:SKILL.md:281:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 281,
        "line_end": 289,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:289:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 289,
        "line_end": 303,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:303:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 303,
        "line_end": 307,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:307:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 307,
        "line_end": 312,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:312:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 312,
        "line_end": 316,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:316:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 316,
        "line_end": 321,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:321:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 321,
        "line_end": 327,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:327:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 327,
        "line_end": 329,
        "snippet": "| strace | ❌ (ptrace not implemented) | `LD_DEBUG=files,libs` |"
      },
      {
        "id": "external_commands:SKILL.md:329:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 329,
        "line_end": 333,
        "snippet": "| gdb | ✓ (with QEMU `-g` flag) | N/A |"
      },
      {
        "id": "external_commands:SKILL.md:333:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 333,
        "line_end": 339,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:339:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 339,
        "line_end": 349,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:349:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 349,
        "line_end": 358,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:358:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 358,
        "line_end": 362,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:362:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 362,
        "line_end": 368,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:368:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 368,
        "line_end": 374,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:374:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 374,
        "line_end": 384,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:384:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 384,
        "line_end": 388,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:388:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 388,
        "line_end": 394,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:394:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 394,
        "line_end": 402,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:402:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 402,
        "line_end": 414,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:414:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 414,
        "line_end": 418,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:418:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 418,
        "line_end": 421,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:421:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 421,
        "line_end": 427,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:427:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 427,
        "line_end": 428,
        "snippet": "| `ptrace(TRACEME)` | Returns EPERM if debugger attached | Patch call to NOP, use QEMU |"
      },
      {
        "id": "external_commands:SKILL.md:428:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 428,
        "line_end": 429,
        "snippet": "| `/proc/self/status` check | Reads TracerPid field | Use QEMU (no /proc emulation) |"
      },
      {
        "id": "external_commands:SKILL.md:429:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 429,
        "line_end": 429,
        "snippet": "| Timing checks | `gettimeofday`/`rdtsc` loops | Single-step with GDB, patch checks |"
      },
      {
        "id": "external_commands:SKILL.md:440:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 440,
        "line_end": 441,
        "snippet": "| `Unsupported syscall` | QEMU limitation | Try Qiling or on-device |"
      },
      {
        "id": "external_commands:SKILL.md:441:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 441,
        "line_end": 441,
        "snippet": "| `Invalid ELF image` | Wrong arch/sysroot | Verify `file` output |"
      },
      {
        "id": "external_commands:SKILL.md:442:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 442,
        "line_end": 442,
        "snippet": "| `Segfault at 0x0` | Missing library | Check `ldd` equivalent |"
      },
      {
        "id": "external_commands:SKILL.md:443:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 443,
        "line_end": 444,
        "snippet": "| `QEMU hangs` | Blocking on I/O | Add timeout, check strace |"
      },
      {
        "id": "external_commands:SKILL.md:444:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 444,
        "line_end": 445,
        "snippet": "| `Anti-debugging` | Detection code | Use Frida stalker mode |"
      },
      {
        "id": "external_commands:SKILL.md:445:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 445,
        "line_end": 445,
        "snippet": "| `exec format error` in Docker | binfmt not registered | Run `tonistiigi/binfmt --install arm` |"
      },
      {
        "id": "external_commands:SKILL.md:446:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 446,
        "line_end": 447,
        "snippet": "| `ld-linux.so.3 not found` | Linker path mismatch | Create symlink in container |"
      },
      {
        "id": "external_commands:SKILL.md:447:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 447,
        "line_end": 447,
        "snippet": "| `libXXX.so not found` | Missing dependency | `apt install` in container |"
      },
      {
        "id": "external_commands:SKILL.md:448:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 448,
        "line_end": 448,
        "snippet": "| Empty mount in Docker | Colima /tmp issue | Use `~/` path instead of `/tmp/` |"
      },
      {
        "id": "external_commands:SKILL.md:449:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 449,
        "line_end": 449,
        "snippet": "| `ptrace: Operation not permitted` | strace in QEMU | Use `LD_DEBUG` instead |"
      },
      {
        "id": "external_commands:SKILL.md:455:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 455,
        "line_end": 497,
        "snippet": "```json"
      },
      {
        "id": "external_commands:SKILL.md:497:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 497,
        "line_end": 503,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:503:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 503,
        "line_end": 529,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:529:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 529,
        "line_end": 533,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:533:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 533,
        "line_end": 557,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:557:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 557,
        "line_end": 561,
        "snippet": "```"
      },
      {
        "id": "network:SKILL.md:480:hardcoded-ip-address",
        "category": "network",
        "severity": "medium",
        "pattern": "Hardcoded IP address",
        "file": "SKILL.md",
        "line_start": 480,
        "line_end": 480,
        "snippet": "\"address\": \"192.168.1.100\","
      },
      {
        "id": "network:SKILL.md:493:hardcoded-ip-address",
        "category": "network",
        "severity": "medium",
        "pattern": "Hardcoded IP address",
        "file": "SKILL.md",
        "line_start": 493,
        "line_end": 493,
        "snippet": "\"evidence\": \"connect() to 192.168.1.100:8443 observed\""
      },
      {
        "id": "network:SKILL.md:541:hardcoded-ip-address",
        "category": "network",
        "severity": "medium",
        "pattern": "Hardcoded IP address",
        "file": "SKILL.md",
        "line_start": 541,
        "line_end": 541,
        "snippet": "FACT: Binary attempts connect to 93.184.216.34:443 (source: strace connect)"
      },
      {
        "id": "network:SKILL.md:555:hardcoded-ip-address",
        "category": "network",
        "severity": "medium",
        "pattern": "Hardcoded IP address",
        "file": "SKILL.md",
        "line_start": 555,
        "line_end": 555,
        "snippet": "RESOLVED: \"Does it actually phone home?\" → Yes, connect() to 93.184.216.34:443 observed"
      },
      {
        "id": "filesystem:SKILL.md:144:hidden-file-in-home-directory",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Hidden file in home directory",
        "file": "SKILL.md",
        "line_start": 144,
        "line_end": 144,
        "snippet": "-ex \"source ~/.gdbinit-gef.py\" \\"
      },
      {
        "id": "filesystem:SKILL.md:144:hidden-file-access",
        "category": "filesystem",
        "severity": "medium",
        "pattern": "Hidden file access",
        "file": "SKILL.md",
        "line_start": 144,
        "line_end": 144,
        "snippet": "-ex \"source ~/.gdbinit-gef.py\" \\"
      },
      {
        "id": "filesystem:SKILL.md:404:linux-proc-filesystem-access",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Linux /proc filesystem access",
        "file": "SKILL.md",
        "line_start": 404,
        "line_end": 404,
        "snippet": "strings -a binary | grep -Ei 'ptrace|anti|debugger|seccomp|LD_PRELOAD|/proc/self'"
      },
      {
        "id": "filesystem:SKILL.md:413:linux-proc-filesystem-access",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Linux /proc filesystem access",
        "file": "SKILL.md",
        "line_start": 413,
        "line_end": 413,
        "snippet": "# - /proc/self/status checks - Detect TracerPid"
      },
      {
        "id": "filesystem:SKILL.md:420:linux-proc-filesystem-access",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Linux /proc filesystem access",
        "file": "SKILL.md",
        "line_start": 420,
        "line_end": 420,
        "snippet": "strace -f ./binary 2>&1 | grep -E 'ptrace|prctl|seccomp|/proc/self'"
      },
      {
        "id": "filesystem:SKILL.md:428:linux-proc-filesystem-access",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Linux /proc filesystem access",
        "file": "SKILL.md",
        "line_start": 428,
        "line_end": 428,
        "snippet": "| `/proc/self/status` check | Reads TracerPid field | Use QEMU (no /proc emulation) |"
      },
      {
        "id": "filesystem:SKILL.md:295:standard-device-file-access",
        "category": "filesystem",
        "severity": "low",
        "pattern": "Standard device file access",
        "file": "SKILL.md",
        "line_start": 295,
        "line_end": 295,
        "snippet": "ln -sf /lib/ld-linux-armhf.so.3 /lib/ld-linux.so.3 2>/dev/null || true"
      },
      {
        "id": "filesystem:SKILL.md:298:standard-device-file-access",
        "category": "filesystem",
        "severity": "low",
        "pattern": "Standard device file access",
        "file": "SKILL.md",
        "line_start": 298,
        "line_end": 298,
        "snippet": "apt-get update -qq && apt-get install -qq -y libcap2 libacl1 2>/dev/null"
      },
      {
        "id": "filesystem:SKILL.md:52:temp-directory-access",
        "category": "filesystem",
        "severity": "medium",
        "pattern": "Temp directory access",
        "file": "SKILL.md",
        "line_start": 52,
        "line_end": 52,
        "snippet": "docker run -v /tmp/samples:/work:ro ..."
      },
      {
        "id": "filesystem:SKILL.md:170:temp-directory-access",
        "category": "filesystem",
        "severity": "medium",
        "pattern": "Temp directory access",
        "file": "SKILL.md",
        "line_start": 170,
        "line_end": 170,
        "snippet": "dump memory /tmp/mem.bin 0x8000 0x9000  # Extract region"
      },
      {
        "id": "filesystem:SKILL.md:364:temp-directory-access",
        "category": "filesystem",
        "severity": "medium",
        "pattern": "Temp directory access",
        "file": "SKILL.md",
        "line_start": 364,
        "line_end": 364,
        "snippet": "strace -f -o /tmp/trace.log ./binary"
      },
      {
        "id": "filesystem:SKILL.md:367:temp-directory-access",
        "category": "filesystem",
        "severity": "medium",
        "pattern": "Temp directory access",
        "file": "SKILL.md",
        "line_start": 367,
        "line_end": 367,
        "snippet": "scp user@device:/tmp/trace.log ."
      },
      {
        "id": "filesystem:SKILL.md:448:temp-directory-access",
        "category": "filesystem",
        "severity": "medium",
        "pattern": "Temp directory access",
        "file": "SKILL.md",
        "line_start": 448,
        "line_end": 448,
        "snippet": "| Empty mount in Docker | Colima /tmp issue | Use `~/` path instead of `/tmp/` |"
      },
      {
        "id": "filesystem:SKILL.md:295:symlink-creation",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Symlink creation",
        "file": "SKILL.md",
        "line_start": 295,
        "line_end": 295,
        "snippet": "ln -sf /lib/ld-linux-armhf.so.3 /lib/ld-linux.so.3 2>/dev/null || true"
      },
      {
        "id": "filesystem:SKILL.md:178:memory-mapped-file-access",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Memory-mapped file access",
        "file": "SKILL.md",
        "line_start": 178,
        "line_end": 178,
        "snippet": "gef> vmmap                 # Memory layout"
      },
      {
        "id": "blocker:SKILL.md:542:log-file-deletion",
        "category": "blocker",
        "severity": "critical",
        "pattern": "Log file deletion",
        "file": "SKILL.md",
        "line_start": 542,
        "line_end": 542,
        "snippet": "FACT: Binary writes to /var/log/thermostat.log (source: strace openat O_WRONLY)"
      },
      {
        "id": "blocker:SKILL.md:556:log-file-deletion",
        "category": "blocker",
        "severity": "critical",
        "pattern": "Log file deletion",
        "file": "SKILL.md",
        "line_start": 556,
        "line_end": 556,
        "snippet": "RESOLVED: \"What files does it access?\" → /etc/thermostat.conf (read), /var/log/thermostat.log (write"
      },
      {
        "id": "blocker:SKILL.md:39:docker-privileged-mode",
        "category": "blocker",
        "severity": "critical",
        "pattern": "Docker privileged mode",
        "file": "SKILL.md",
        "line_start": 39,
        "line_end": 39,
        "snippet": "docker run --rm --privileged --platform linux/arm64 \\"
      },
      {
        "id": "blocker:SKILL.md:413:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 413,
        "line_end": 414,
        "snippet": "# - /proc/self/status checks - Detect TracerPid"
      },
      {
        "id": "blocker:SKILL.md:428:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 428,
        "line_end": 428,
        "snippet": "| `/proc/self/status` check | Reads TracerPid field | Use QEMU (no /proc emulation) |"
      },
      {
        "id": "blocker:SKILL.md:441:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 441,
        "line_end": 441,
        "snippet": "| `Invalid ELF image` | Wrong arch/sysroot | Verify `file` output |"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:27:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:29:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:34:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:41:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:45:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:47:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:53:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:73:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:82:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:88:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:89:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:90:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:91:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:95:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:107:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:113:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:128:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:136:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:146:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:150:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:171:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:177:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:183:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:187:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:202:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:217:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:218:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:224:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:228:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:246:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:248:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:251:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:255:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:269:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:273:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:281:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:289:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:303:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:307:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:312:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:316:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:321:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:327:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:329:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:333:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:339:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:349:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:358:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:362:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:368:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:374:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:384:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:388:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:394:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:402:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:414:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:418:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "id": "external_commands:SKILL.md:421:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:427:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:428:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:429:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:440:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:441:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:442:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:443:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:444:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:445:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:446:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:447:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:448:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:449:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:455:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:497:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:503:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:529:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:533:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "external_commands:SKILL.md:557:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.87,
        "reason": "The flagged text is Markdown formatting, a table entry, a troubleshooting note, or an output template rather than an instruction that directly executes a command."
      },
      {
        "id": "network:SKILL.md:480:hardcoded-ip-address",
        "verdict": "false_positive",
        "confidence": 0.91,
        "reason": "The IP address appears inside an example observation or journal template, not as a hardcoded destination used by the skill itself. It documents what an analyzed binary might do."
      },
      {
        "id": "network:SKILL.md:493:hardcoded-ip-address",
        "verdict": "false_positive",
        "confidence": 0.91,
        "reason": "The IP address appears inside an example observation or journal template, not as a hardcoded destination used by the skill itself. It documents what an analyzed binary might do."
      },
      {
        "id": "network:SKILL.md:541:hardcoded-ip-address",
        "verdict": "false_positive",
        "confidence": 0.91,
        "reason": "The IP address appears inside an example observation or journal template, not as a hardcoded destination used by the skill itself. It documents what an analyzed binary might do."
      },
      {
        "id": "network:SKILL.md:555:hardcoded-ip-address",
        "verdict": "false_positive",
        "confidence": 0.91,
        "reason": "The IP address appears inside an example observation or journal template, not as a hardcoded destination used by the skill itself. It documents what an analyzed binary might do."
      },
      {
        "id": "filesystem:SKILL.md:144:hidden-file-in-home-directory",
        "verdict": "confirmed",
        "confidence": 0.74,
        "severity": "high",
        "reason": "The GDB example sources a hidden user configuration file, which can execute debugger extensions or Python commands. This is common in RE setups but should be treated as executable local configuration."
      },
      {
        "id": "filesystem:SKILL.md:144:hidden-file-access",
        "verdict": "confirmed",
        "confidence": 0.74,
        "severity": "medium",
        "reason": "The GDB example sources a hidden user configuration file, which can execute debugger extensions or Python commands. This is common in RE setups but should be treated as executable local configuration."
      },
      {
        "id": "filesystem:SKILL.md:404:linux-proc-filesystem-access",
        "verdict": "false_positive",
        "confidence": 0.88,
        "reason": "The /proc references are search terms used to detect anti-debug behavior in a target binary. The skill is not reading host /proc data for reconnaissance."
      },
      {
        "id": "filesystem:SKILL.md:413:linux-proc-filesystem-access",
        "verdict": "false_positive",
        "confidence": 0.88,
        "reason": "The /proc references are search terms used to detect anti-debug behavior in a target binary. The skill is not reading host /proc data for reconnaissance."
      },
      {
        "id": "filesystem:SKILL.md:420:linux-proc-filesystem-access",
        "verdict": "false_positive",
        "confidence": 0.88,
        "reason": "The /proc references are search terms used to detect anti-debug behavior in a target binary. The skill is not reading host /proc data for reconnaissance."
      },
      {
        "id": "filesystem:SKILL.md:428:linux-proc-filesystem-access",
        "verdict": "false_positive",
        "confidence": 0.88,
        "reason": "The /proc references are search terms used to detect anti-debug behavior in a target binary. The skill is not reading host /proc data for reconnaissance."
      },
      {
        "id": "filesystem:SKILL.md:295:standard-device-file-access",
        "verdict": "false_positive",
        "confidence": 0.84,
        "reason": "The flagged filesystem pattern is a benign analysis or package-management artifact in the documented workflow, not evidence of data theft or host persistence."
      },
      {
        "id": "filesystem:SKILL.md:298:standard-device-file-access",
        "verdict": "false_positive",
        "confidence": 0.84,
        "reason": "The flagged filesystem pattern is a benign analysis or package-management artifact in the documented workflow, not evidence of data theft or host persistence."
      },
      {
        "id": "filesystem:SKILL.md:52:temp-directory-access",
        "verdict": "false_positive",
        "confidence": 0.85,
        "reason": "The /tmp paths are examples for mounts, memory dumps, or trace files during analysis. They do not indicate hidden persistence or unauthorized host file access by the skill."
      },
      {
        "id": "filesystem:SKILL.md:170:temp-directory-access",
        "verdict": "false_positive",
        "confidence": 0.85,
        "reason": "The /tmp paths are examples for mounts, memory dumps, or trace files during analysis. They do not indicate hidden persistence or unauthorized host file access by the skill."
      },
      {
        "id": "filesystem:SKILL.md:364:temp-directory-access",
        "verdict": "false_positive",
        "confidence": 0.85,
        "reason": "The /tmp paths are examples for mounts, memory dumps, or trace files during analysis. They do not indicate hidden persistence or unauthorized host file access by the skill."
      },
      {
        "id": "filesystem:SKILL.md:367:temp-directory-access",
        "verdict": "false_positive",
        "confidence": 0.85,
        "reason": "The /tmp paths are examples for mounts, memory dumps, or trace files during analysis. They do not indicate hidden persistence or unauthorized host file access by the skill."
      },
      {
        "id": "filesystem:SKILL.md:448:temp-directory-access",
        "verdict": "false_positive",
        "confidence": 0.85,
        "reason": "The /tmp paths are examples for mounts, memory dumps, or trace files during analysis. They do not indicate hidden persistence or unauthorized host file access by the skill."
      },
      {
        "id": "filesystem:SKILL.md:295:symlink-creation",
        "verdict": "confirmed",
        "confidence": 0.78,
        "severity": "high",
        "reason": "The Docker example creates or overwrites a system linker symlink as root inside the container. It is intended for container repair but is dangerous if run outside the intended isolation."
      },
      {
        "id": "filesystem:SKILL.md:178:memory-mapped-file-access",
        "verdict": "false_positive",
        "confidence": 0.84,
        "reason": "The flagged filesystem pattern is a benign analysis or package-management artifact in the documented workflow, not evidence of data theft or host persistence."
      },
      {
        "id": "blocker:SKILL.md:542:log-file-deletion",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The text is an example journal entry saying a target binary writes a log file. It does not instruct deletion or tampering with logs."
      },
      {
        "id": "blocker:SKILL.md:556:log-file-deletion",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The text is an example journal entry saying a target binary writes a log file. It does not instruct deletion or tampering with logs."
      },
      {
        "id": "blocker:SKILL.md:39:docker-privileged-mode",
        "verdict": "confirmed",
        "confidence": 0.93,
        "severity": "critical",
        "reason": "The setup command explicitly runs Docker with --privileged to register binfmt handlers. This expands container permissions over the host and is a real high-impact action."
      },
      {
        "id": "blocker:SKILL.md:413:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.86,
        "reason": "The flagged text describes how a target binary may detect debuggers or how to verify file format issues. It is analysis guidance, not host reconnaissance by the skill."
      },
      {
        "id": "blocker:SKILL.md:428:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.86,
        "reason": "The flagged text describes how a target binary may detect debuggers or how to verify file format issues. It is analysis guidance, not host reconnaissance by the skill."
      },
      {
        "id": "blocker:SKILL.md:441:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.86,
        "reason": "The flagged text describes how a target binary may detect debuggers or how to verify file format issues. It is analysis guidance, not host reconnaissance by the skill."
      }
    ],
    "semantic_findings": [
      {
        "title": "Low-Isolation On-Device Execution Path",
        "description": "The skill presents on-device analysis as an option when emulation fails and notes that on-device isolation is low. Running unknown binaries on real targets can expose the device, credentials, and attached networks if not tightly controlled.",
        "severity": "high",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 343,
            "line_end": 367
          }
        ],
        "confidence": 0.82,
        "confidence_reasoning": "The analysis options explicitly rate on-device isolation as low, and the on-device section includes commands to run the binary and pull traces from a target device."
      },
      {
        "title": "Anti-Analysis Bypass Guidance",
        "description": "The skill explains how to identify and bypass anti-debugging checks, including patching ptrace and using QEMU to avoid /proc-based debugger detection. This is legitimate in authorized reverse engineering but is dual-use and should be framed with stronger authorization boundaries.",
        "severity": "medium",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 423,
            "line_end": 432
          }
        ],
        "confidence": 0.79,
        "confidence_reasoning": "The cited section directly lists anti-analysis patterns and bypass techniques. The surrounding purpose is defensive analysis, so the risk is dual-use rather than clearly malicious."
      }
    ],
    "critical_findings": [
      {
        "title": "Docker privileged mode",
        "description": "docker run --rm --privileged --platform linux/arm64 \\",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 39,
            "line_end": 39
          }
        ],
        "review_kind": "security",
        "source_category": "blocker",
        "source_severity": "critical",
        "confidence": 0.93,
        "confidence_reasoning": "The setup command explicitly runs Docker with --privileged to register binfmt handlers. This expands container permissions over the host and is a real high-impact action."
      }
    ],
    "high_findings": [
      {
        "title": "Hidden file in home directory",
        "description": "-ex \"source ~/.gdbinit-gef.py\" \\",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 144,
            "line_end": 144
          }
        ],
        "review_kind": "capability",
        "source_category": "filesystem",
        "source_severity": "high",
        "confidence": 0.74,
        "confidence_reasoning": "The GDB example sources a hidden user configuration file, which can execute debugger extensions or Python commands. This is common in RE setups but should be treated as executable local configuration."
      },
      {
        "title": "Symlink creation",
        "description": "ln -sf /lib/ld-linux-armhf.so.3 /lib/ld-linux.so.3 2>/dev/null || true",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 295,
            "line_end": 295
          }
        ],
        "review_kind": "capability",
        "source_category": "filesystem",
        "source_severity": "high",
        "confidence": 0.78,
        "confidence_reasoning": "The Docker example creates or overwrites a system linker symlink as root inside the container. It is intended for container repair but is dangerous if run outside the intended isolation."
      },
      {
        "title": "Low-Isolation On-Device Execution Path",
        "description": "The skill presents on-device analysis as an option when emulation fails and notes that on-device isolation is low. Running unknown binaries on real targets can expose the device, credentials, and attached networks if not tightly controlled.",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 343,
            "line_end": 367
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "high",
        "confidence": 0.82,
        "confidence_reasoning": "The analysis options explicitly rate on-device isolation as low, and the on-device section includes commands to run the binary and pull traces from a target device."
      }
    ],
    "medium_findings": [
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 34,
            "line_end": 41
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 47,
            "line_end": 53
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 73,
            "line_end": 82
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 95,
            "line_end": 107
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 136,
            "line_end": 146
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```gdb",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 150,
            "line_end": 171
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```gdb",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 177,
            "line_end": 183
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 187,
            "line_end": 202
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "For cross-arch Frida, deploy `frida-server` to the target device:",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 217,
            "line_end": 218
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 218,
            "line_end": 224
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```javascript",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 228,
            "line_end": 246
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 248,
            "line_end": 251
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```javascript",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 255,
            "line_end": 269
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```javascript",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 273,
            "line_end": 281
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 289,
            "line_end": 303
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 307,
            "line_end": 312
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 316,
            "line_end": 321
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 333,
            "line_end": 339
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 349,
            "line_end": 358
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 362,
            "line_end": 368
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 374,
            "line_end": 384
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 388,
            "line_end": 394
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 402,
            "line_end": 414
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 418,
            "line_end": 421
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This section provides executable dynamic-analysis or instrumentation commands for running or attaching to binaries. The use is legitimate for authorized research, but it can execute untrusted code if copied without a sandbox."
      },
      {
        "title": "Hidden file access",
        "description": "-ex \"source ~/.gdbinit-gef.py\" \\",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 144,
            "line_end": 144
          }
        ],
        "review_kind": "capability",
        "source_category": "filesystem",
        "source_severity": "medium",
        "confidence": 0.74,
        "confidence_reasoning": "The GDB example sources a hidden user configuration file, which can execute debugger extensions or Python commands. This is common in RE setups but should be treated as executable local configuration."
      },
      {
        "title": "Anti-Analysis Bypass Guidance",
        "description": "The skill explains how to identify and bypass anti-debugging checks, including patching ptrace and using QEMU to avoid /proc-based debugger detection. This is legitimate in authorized reverse engineering but is dual-use and should be framed with stronger authorization boundaries.",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 423,
            "line_end": 432
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "medium",
        "confidence": 0.79,
        "confidence_reasoning": "The cited section directly lists anti-analysis patterns and bypass techniques. The surrounding purpose is defensive analysis, so the risk is dual-use rather than clearly malicious."
      }
    ],
    "low_findings": [],
    "dangerous_patterns": [
      {
        "title": "Docker privileged mode",
        "description": "docker run --rm --privileged --platform linux/arm64 \\",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 39,
            "line_end": 39
          }
        ],
        "review_kind": "security",
        "source_category": "blocker",
        "source_severity": "critical",
        "confidence": 0.93,
        "confidence_reasoning": "The setup command explicitly runs Docker with --privileged to register binfmt handlers. This expands container permissions over the host and is a real high-impact action."
      }
    ],
    "files_scanned": 1,
    "total_lines": 564,
    "audit_model": "claude",
    "audited_at": "2026-07-09T01:41:28.477Z",
    "agent_auto_install_policy": "blocked",
    "manual_install_policy": "allowed_with_warning"
  },
  "content": {
    "user_title": "Analyze Binary Runtime Behavior",
    "value_statement": "Unknown binaries can hide behavior that static review cannot confirm. This skill guides controlled execution, tracing, debugging, and evidence capture for dynamic analysis.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "binary reverse engineering",
      "dynamic analysis",
      "QEMU tracing",
      "GDB debugging",
      "Frida hooking",
      "syscall tracing",
      "malware analysis"
    ],
    "actual_capabilities": [
      "Selects QEMU, Docker, GDB, Frida, or on-device analysis based on host and target architecture.",
      "Provides commands for syscall tracing, remote debugging, memory inspection, and function interception.",
      "Defines sandbox checks and requires human approval before any binary execution.",
      "Shows how to capture network, file, process, and memory observations from runtime behavior.",
      "Documents anti-analysis indicators and troubleshooting steps for emulation and debugging failures.",
      "Supplies structured journaling formats for reproducible dynamic-analysis findings."
    ],
    "limitations": [
      "It cannot make unknown binaries safe to execute without a properly isolated environment.",
      "Frida guidance requires native-architecture execution or a target device with frida-server.",
      "Some workflows require privileged Docker, ptrace, network controls, or system-specific tooling.",
      "The skill provides methodology and examples, not automated malware containment."
    ],
    "use_cases": [
      {
        "title": "Validate suspected network behavior",
        "description": "Run a sample in a network-controlled sandbox and confirm outbound connection attempts with syscall traces.",
        "target_user": "Security analyst"
      },
      {
        "title": "Debug cross-architecture firmware tools",
        "description": "Use QEMU and GDB to execute ARM or MIPS binaries from a Linux or macOS workstation.",
        "target_user": "Firmware reverse engineer"
      },
      {
        "title": "Capture runtime evidence for reports",
        "description": "Record file access, process activity, network events, and hypothesis updates in a consistent analysis journal.",
        "target_user": "Incident response team"
      }
    ],
    "prompt_templates": [
      {
        "title": "Choose a safe analysis method",
        "scenario": "Beginner planning before execution",
        "prompt": "I have an unknown Linux ARM binary. Help me choose the safest dynamic analysis method and list the approvals and sandbox settings needed before running it."
      },
      {
        "title": "Trace runtime behavior",
        "scenario": "Syscall-focused observation",
        "prompt": "Guide me through tracing this binary with QEMU or strace. I need to identify file access, process creation, and network attempts without allowing real outbound traffic."
      },
      {
        "title": "Debug a suspicious branch",
        "scenario": "Instruction-level debugging",
        "prompt": "Help me attach GDB to a cross-architecture binary under QEMU, set breakpoints near the suspected check, and collect register and memory evidence."
      },
      {
        "title": "Instrument function calls",
        "scenario": "Advanced dynamic instrumentation",
        "prompt": "Create a Frida-based dynamic analysis plan for a native binary. I want to intercept network-related functions, log arguments, and preserve evidence for a final report."
      }
    ],
    "output_examples": [
      {
        "input": "Analyze whether this ARM binary contacts a server during startup.",
        "output": "The workflow recommends QEMU syscall tracing inside a network-blocked sandbox, followed by evidence notes for socket creation, connection attempts, and timing behavior."
      },
      {
        "input": "The binary fails under emulation with a missing loader error.",
        "output": "The response identifies a likely sysroot or linker mismatch, suggests checking the binary architecture, and recommends a container or corrected library path."
      },
      {
        "input": "I need proof that a function receives a secret at runtime.",
        "output": "The skill guides GDB breakpoints or Frida hooks, then asks for captured arguments, memory context, and a confidence update in the analysis journal."
      }
    ],
    "best_practices": [
      "Get explicit human approval and document the sandbox before executing any binary.",
      "Prefer QEMU or a network-blocked container before lower-isolation on-device execution.",
      "Record each runtime claim with the tool output or observation that supports it."
    ],
    "anti_patterns": [
      "Do not run unknown binaries directly on a workstation without isolation and resource limits.",
      "Do not enable privileged Docker or device access without understanding the host impact.",
      "Do not treat example IP addresses, paths, or journal entries as evidence from a real sample."
    ],
    "faq": [
      {
        "question": "Does this skill execute binaries automatically?",
        "answer": "No. It gives workflows and commands, and it states that human approval is required before execution."
      },
      {
        "question": "What tools does it cover?",
        "answer": "It covers QEMU user mode, GDB, gdbserver, Frida, Docker, strace, LD_DEBUG, nsjail, and related troubleshooting."
      },
      {
        "question": "Is it suitable for malware analysis?",
        "answer": "It can support authorized malware analysis when used inside a properly isolated and monitored environment."
      },
      {
        "question": "Can it analyze cross-architecture binaries?",
        "answer": "Yes. It includes ARM, ARM64, MIPS, and x86 32-bit workflows using QEMU, Docker, or target devices."
      },
      {
        "question": "Does it require privileged access?",
        "answer": "Some setup paths use privileged Docker or target-device debugging. Those steps require careful review and approval."
      },
      {
        "question": "What output should users expect?",
        "answer": "Users should expect runtime observations, syscall summaries, debugger notes, function-hook evidence, and updated hypotheses."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 564
    }
  ]
}
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall