{
  "schemaVersion": "1.0",
  "item": {
    "slug": "skulk-skill-scanner",
    "name": "Skulk Skill Scanner",
    "source": "tencent",
    "type": "skill",
    "category": "安全合规",
    "sourceUrl": "https://clawhub.ai/AdaInTheLab/skulk-skill-scanner",
    "canonicalUrl": "https://clawhub.ai/AdaInTheLab/skulk-skill-scanner",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/skulk-skill-scanner",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skulk-skill-scanner",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "_meta.json",
      "scripts/scanner.js"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/skulk-skill-scanner"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/skulk-skill-scanner",
    "agentPageUrl": "https://openagent3.xyz/skills/skulk-skill-scanner/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skulk-skill-scanner/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skulk-skill-scanner/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Skill Scanner",
        "body": "Security scanner for OpenClaw agent skills. Static analysis for red flags."
      },
      {
        "title": "Usage",
        "body": "node scripts/scanner.js <path-to-skill> [--verbose] [--json] [--summary] [--ignore <path>] [--include-self]"
      },
      {
        "title": "Examples",
        "body": "# Scan a downloaded skill folder before enabling it\nclawhub inspect some-skill\nnode scripts/scanner.js ./skills/some-skill --verbose\n\n# Scan your own skill before publishing\nnode scripts/scanner.js ./skills/my-skill\n\n# JSON output for automation\nnode scripts/scanner.js ./skills/my-skill --json\n\n# One-line summary output for heartbeat checks\nnode scripts/scanner.js ./skills/my-skill --summary\n\n# Include scanner internals (off by default to reduce self-scan noise)\nnode scripts/scanner.js ./skills/skulk-skill-scanner --include-self"
      },
      {
        "title": "What It Catches",
        "body": "SeverityFlags🔴 CriticalData exfiltration, credential access, safety overrides, destructive commands🟠 HighObfuscation (base64/eval), unknown network access, env scanning, privilege escalation, hidden instructions🟡 MediumWrites outside workspace, package installs (supply chain), messaging on user's behalf, persistent timers/automation🔵 InfoAPI key references, broad tool access requests"
      },
      {
        "title": "Scoring",
        "body": "Each unique rule deducts points: critical=30, high=15, medium=5, info=0\nScore 75-100: ✅ PASS\nScore 50-74: ⚠️ WARN\nScore 0-49 or any critical: ❌ FAIL\nExit code 1 on FAIL (CI-friendly)"
      },
      {
        "title": "Safe Domain Allowlist",
        "body": "Known legitimate API domains are allowlisted to reduce false positives on network-related rules. Edit the SAFE_DOMAINS array in scripts/scanner.js to customize."
      },
      {
        "title": "Limitations",
        "body": "This is static pattern matching — it catches obvious and moderately obfuscated attacks but cannot detect:\n\nSophisticated multi-step social engineering\nRuntime-generated URLs or dynamic exfiltration\nAttacks that look identical to legitimate skill behavior\n\nIt's a first line of defense, not a guarantee. Always review skills manually before granting sensitive access."
      }
    ],
    "body": "Skill Scanner\n\nSecurity scanner for OpenClaw agent skills. Static analysis for red flags.\n\nUsage\nnode scripts/scanner.js <path-to-skill> [--verbose] [--json] [--summary] [--ignore <path>] [--include-self]\n\nExamples\n# Scan a downloaded skill folder before enabling it\nclawhub inspect some-skill\nnode scripts/scanner.js ./skills/some-skill --verbose\n\n# Scan your own skill before publishing\nnode scripts/scanner.js ./skills/my-skill\n\n# JSON output for automation\nnode scripts/scanner.js ./skills/my-skill --json\n\n# One-line summary output for heartbeat checks\nnode scripts/scanner.js ./skills/my-skill --summary\n\n# Include scanner internals (off by default to reduce self-scan noise)\nnode scripts/scanner.js ./skills/skulk-skill-scanner --include-self\n\nWhat It Catches\nSeverity\tFlags\n🔴 Critical\tData exfiltration, credential access, safety overrides, destructive commands\n🟠 High\tObfuscation (base64/eval), unknown network access, env scanning, privilege escalation, hidden instructions\n🟡 Medium\tWrites outside workspace, package installs (supply chain), messaging on user's behalf, persistent timers/automation\n🔵 Info\tAPI key references, broad tool access requests\nScoring\nEach unique rule deducts points: critical=30, high=15, medium=5, info=0\nScore 75-100: ✅ PASS\nScore 50-74: ⚠️ WARN\nScore 0-49 or any critical: ❌ FAIL\nExit code 1 on FAIL (CI-friendly)\nSafe Domain Allowlist\n\nKnown legitimate API domains are allowlisted to reduce false positives on network-related rules. Edit the SAFE_DOMAINS array in scripts/scanner.js to customize.\n\nLimitations\n\nThis is static pattern matching — it catches obvious and moderately obfuscated attacks but cannot detect:\n\nSophisticated multi-step social engineering\nRuntime-generated URLs or dynamic exfiltration\nAttacks that look identical to legitimate skill behavior\n\nIt's a first line of defense, not a guarantee. Always review skills manually before granting sensitive access."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/AdaInTheLab/skulk-skill-scanner",
    "publisherUrl": "https://clawhub.ai/AdaInTheLab/skulk-skill-scanner",
    "owner": "AdaInTheLab",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/skulk-skill-scanner",
    "downloadUrl": "https://openagent3.xyz/downloads/skulk-skill-scanner",
    "agentUrl": "https://openagent3.xyz/skills/skulk-skill-scanner/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skulk-skill-scanner/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skulk-skill-scanner/agent.md"
  }
}