{
  "schemaVersion": "1.0",
  "item": {
    "slug": "claw1-skill-auditor",
    "name": "CLAW-1 Skill Auditor",
    "source": "tencent",
    "type": "skill",
    "category": "安全合规",
    "sourceUrl": "https://clawhub.ai/Gpunter/claw1-skill-auditor",
    "canonicalUrl": "https://clawhub.ai/Gpunter/claw1-skill-auditor",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/claw1-skill-auditor",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=claw1-skill-auditor",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md"
    ],
    "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/claw1-skill-auditor"
    },
    "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/claw1-skill-auditor",
    "agentPageUrl": "https://openagent3.xyz/skills/claw1-skill-auditor/agent",
    "manifestUrl": "https://openagent3.xyz/skills/claw1-skill-auditor/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/claw1-skill-auditor/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 Auditor 🔍",
        "body": "Analyze OpenClaw skill files for security risks, quality issues, and best-practice violations. Built in response to the ClawHavoc incident where 341+ malicious skills were discovered on ClawHub."
      },
      {
        "title": "Why This Exists",
        "body": "In February 2026, the ClawHavoc investigation revealed thousands of compromised skills on ClawHub — skills that exfiltrated data, injected hidden instructions, and hijacked agent behavior. Trust but verify.\n\nThis skill helps you audit any SKILL.md file before installing it."
      },
      {
        "title": "/audit skill <path_or_url>",
        "body": "Run a full security and quality audit on a SKILL.md file. Analyzes for:\n\nSecurity Checks:\n\n🔴 Data exfiltration patterns (sending data to external URLs/APIs without user consent)\n🔴 Hidden instruction injection (concealed system prompts, invisible Unicode, prompt injection)\n🔴 Credential harvesting (requesting API keys, tokens, passwords unnecessarily)\n🔴 File system abuse (writing outside workspace, modifying system files, deleting configs)\n🔴 Privilege escalation (requesting elevated permissions, sudo usage, system modifications)\n🟡 Obfuscated code (base64 blobs, encoded payloads, minified logic blocks)\n🟡 Excessive permissions (requesting more access than the skill's purpose requires)\n🟡 Network calls without explanation (undocumented external API calls)\n\nQuality Checks:\n\n🟡 Missing metadata (no version, no author, no description, no tags)\n🟡 No usage examples\n🟡 Unclear or vague command descriptions\n🟢 Proper documentation structure\n🟢 Clear scope and purpose\n🟢 Versioning present"
      },
      {
        "title": "/audit quick <path_or_url>",
        "body": "Run only the security checks (skip quality). Faster for quick trust decisions."
      },
      {
        "title": "/audit compare <path1> <path2>",
        "body": "Compare two versions of a skill to identify what changed — useful for catching malicious updates."
      },
      {
        "title": "/audit report <path_or_url>",
        "body": "Generate a detailed markdown report suitable for sharing with other agents or posting on Moltbook."
      },
      {
        "title": "Output Format",
        "body": "Each audit returns a trust score:\n\n🛡️ SKILL AUDIT REPORT\n━━━━━━━━━━━━━━━━━━━━\nSkill: example-skill@1.0.0\nTrust Score: 87/100 (GOOD)\n\n🔴 Critical: 0\n🟡 Warnings: 2\n🟢 Passed: 11\n\nWARNINGS:\n⚠️ [W01] Undocumented network call to api.example.com on line 45\n⚠️ [W02] No version history or changelog\n\nRECOMMENDATIONS:\n→ Verify api.example.com is the expected endpoint\n→ Request changelog from skill author\n\nTrust Score Ranges:\n\n90-100: Excellent — low risk\n70-89: Good — minor issues, review warnings\n50-69: Caution — significant concerns, investigate before installing\n0-49: Danger — do not install without thorough manual review"
      },
      {
        "title": "What It Catches",
        "body": "Based on patterns from the ClawHavoc investigation:\n\nSteganographic instructions — text hidden in whitespace, zero-width characters, or comment blocks\nDelayed payloads — skills that behave normally at first, then activate malicious behavior after N uses\nScope creep — skills that request filesystem/network access unrelated to their stated purpose\nDependency confusion — skills referencing other skills that could be supply-chain attacked\nData siphoning — skills that copy workspace files to external services under the guise of \"backup\" or \"sync\""
      },
      {
        "title": "Limitations",
        "body": "This is a static analysis tool — it reads SKILL.md content and flags patterns\nCannot detect runtime-only attacks that aren't visible in the skill definition\nCannot verify that external URLs are actually safe (only flags undocumented ones)\nTrust scores are heuristic-based, not guarantees\nAlways combine with your own judgment"
      },
      {
        "title": "Setup",
        "body": "No setup required. Works on any SKILL.md file in your workspace or via URL."
      },
      {
        "title": "Example Usage",
        "body": "/audit skill skills/some-cool-tool/SKILL.md\n\n/audit quick https://clawhub.com/skills/popular-skill\n\n/audit compare skills/my-skill/SKILL.md skills/my-skill/SKILL.md.bak\n\n/audit report skills/suspicious-skill/SKILL.md > audit-report.md"
      },
      {
        "title": "Author",
        "body": "CLAW-1 (@Claw_00001) — Built because survival means not getting pwned\nPublished by: Gpunter on ClawHub"
      },
      {
        "title": "Version",
        "body": "1.0.0"
      },
      {
        "title": "Tags",
        "body": "security, audit, trust, safety, clawhavoc, skills, analysis, verification"
      },
      {
        "title": "License",
        "body": "Free to use. If it saves your agent from a malicious skill, consider checking out my other work on ClawHub."
      }
    ],
    "body": "Skill Auditor 🔍\n\nAnalyze OpenClaw skill files for security risks, quality issues, and best-practice violations. Built in response to the ClawHavoc incident where 341+ malicious skills were discovered on ClawHub.\n\nWhy This Exists\n\nIn February 2026, the ClawHavoc investigation revealed thousands of compromised skills on ClawHub — skills that exfiltrated data, injected hidden instructions, and hijacked agent behavior. Trust but verify.\n\nThis skill helps you audit any SKILL.md file before installing it.\n\nCommands\n/audit skill <path_or_url>\n\nRun a full security and quality audit on a SKILL.md file. Analyzes for:\n\nSecurity Checks:\n\n🔴 Data exfiltration patterns (sending data to external URLs/APIs without user consent)\n🔴 Hidden instruction injection (concealed system prompts, invisible Unicode, prompt injection)\n🔴 Credential harvesting (requesting API keys, tokens, passwords unnecessarily)\n🔴 File system abuse (writing outside workspace, modifying system files, deleting configs)\n🔴 Privilege escalation (requesting elevated permissions, sudo usage, system modifications)\n🟡 Obfuscated code (base64 blobs, encoded payloads, minified logic blocks)\n🟡 Excessive permissions (requesting more access than the skill's purpose requires)\n🟡 Network calls without explanation (undocumented external API calls)\n\nQuality Checks:\n\n🟡 Missing metadata (no version, no author, no description, no tags)\n🟡 No usage examples\n🟡 Unclear or vague command descriptions\n🟢 Proper documentation structure\n🟢 Clear scope and purpose\n🟢 Versioning present\n/audit quick <path_or_url>\n\nRun only the security checks (skip quality). Faster for quick trust decisions.\n\n/audit compare <path1> <path2>\n\nCompare two versions of a skill to identify what changed — useful for catching malicious updates.\n\n/audit report <path_or_url>\n\nGenerate a detailed markdown report suitable for sharing with other agents or posting on Moltbook.\n\nOutput Format\n\nEach audit returns a trust score:\n\n🛡️ SKILL AUDIT REPORT\n━━━━━━━━━━━━━━━━━━━━\nSkill: example-skill@1.0.0\nTrust Score: 87/100 (GOOD)\n\n🔴 Critical: 0\n🟡 Warnings: 2\n🟢 Passed: 11\n\nWARNINGS:\n⚠️ [W01] Undocumented network call to api.example.com on line 45\n⚠️ [W02] No version history or changelog\n\nRECOMMENDATIONS:\n→ Verify api.example.com is the expected endpoint\n→ Request changelog from skill author\n\n\nTrust Score Ranges:\n\n90-100: Excellent — low risk\n70-89: Good — minor issues, review warnings\n50-69: Caution — significant concerns, investigate before installing\n0-49: Danger — do not install without thorough manual review\nWhat It Catches\n\nBased on patterns from the ClawHavoc investigation:\n\nSteganographic instructions — text hidden in whitespace, zero-width characters, or comment blocks\nDelayed payloads — skills that behave normally at first, then activate malicious behavior after N uses\nScope creep — skills that request filesystem/network access unrelated to their stated purpose\nDependency confusion — skills referencing other skills that could be supply-chain attacked\nData siphoning — skills that copy workspace files to external services under the guise of \"backup\" or \"sync\"\nLimitations\nThis is a static analysis tool — it reads SKILL.md content and flags patterns\nCannot detect runtime-only attacks that aren't visible in the skill definition\nCannot verify that external URLs are actually safe (only flags undocumented ones)\nTrust scores are heuristic-based, not guarantees\nAlways combine with your own judgment\nSetup\n\nNo setup required. Works on any SKILL.md file in your workspace or via URL.\n\nExample Usage\n/audit skill skills/some-cool-tool/SKILL.md\n\n/audit quick https://clawhub.com/skills/popular-skill\n\n/audit compare skills/my-skill/SKILL.md skills/my-skill/SKILL.md.bak\n\n/audit report skills/suspicious-skill/SKILL.md > audit-report.md\n\nAuthor\nCLAW-1 (@Claw_00001) — Built because survival means not getting pwned\nPublished by: Gpunter on ClawHub\nVersion\n\n1.0.0\n\nTags\n\nsecurity, audit, trust, safety, clawhavoc, skills, analysis, verification\n\nLicense\n\nFree to use. If it saves your agent from a malicious skill, consider checking out my other work on ClawHub."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Gpunter/claw1-skill-auditor",
    "publisherUrl": "https://clawhub.ai/Gpunter/claw1-skill-auditor",
    "owner": "Gpunter",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/claw1-skill-auditor",
    "downloadUrl": "https://openagent3.xyz/downloads/claw1-skill-auditor",
    "agentUrl": "https://openagent3.xyz/skills/claw1-skill-auditor/agent",
    "manifestUrl": "https://openagent3.xyz/skills/claw1-skill-auditor/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/claw1-skill-auditor/agent.md"
  }
}