{
  "schemaVersion": "1.0",
  "item": {
    "slug": "agxntsix-skill-auditor",
    "name": "Skill Auditor",
    "source": "tencent",
    "type": "skill",
    "category": "安全合规",
    "sourceUrl": "https://clawhub.ai/aiwithabidi/agxntsix-skill-auditor",
    "canonicalUrl": "https://clawhub.ai/aiwithabidi/agxntsix-skill-auditor",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/agxntsix-skill-auditor",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agxntsix-skill-auditor",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/known-patterns.md",
      "references/prompt-injection-patterns.md",
      "scripts/audit_skill.py",
      "scripts/quarantine.sh"
    ],
    "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/agxntsix-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/agxntsix-skill-auditor",
    "agentPageUrl": "https://openagent3.xyz/skills/agxntsix-skill-auditor/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agxntsix-skill-auditor/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agxntsix-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": "Security gatekeeper for third-party skill installation. No skill gets installed without passing audit."
      },
      {
        "title": "When to Use",
        "body": "Before installing ANY skill from ClawHub or external sources\nWhen asked to review/evaluate a skill's safety\nWhen clawhub install or similar installation is requested"
      },
      {
        "title": "1. Quarantine First",
        "body": "Never copy a skill directly to the production skills directory. Always quarantine first:\n\nbash skills/skill-auditor/scripts/quarantine.sh /path/to/skill-source\n\nThis copies the skill to a temp directory, runs the full audit, and only allows installation if the risk score is CLEAN or LOW."
      },
      {
        "title": "2. Manual Audit (Python Script Directly)",
        "body": "For inspection without the quarantine wrapper:\n\npython3 skills/skill-auditor/scripts/audit_skill.py /path/to/skill-dir\n\nOutputs JSON report to stdout. Add --human for formatted text output."
      },
      {
        "title": "3. Interpreting Results",
        "body": "RatingActionCLEANSafe to installLOWSafe, minor notes — review findings brieflyMEDIUMDo NOT install without manual review of each findingHIGHBlock installation — likely malicious patterns detectedCRITICALBlock immediately — active threat indicators (exfil, prompt injection, obfuscated payloads)"
      },
      {
        "title": "4. Exit Codes",
        "body": "0 = CLEAN or LOW (safe)\n1 = MEDIUM (needs review)\n2 = HIGH or CRITICAL (blocked)"
      },
      {
        "title": "What Gets Scanned",
        "body": "All files: inventory, sizes, suspicious file types\nCode: shell commands, network calls, env access, filesystem escape, obfuscation, dynamic imports\nSKILL.md: prompt injection patterns, permission scope requests\nDependencies: requirements.txt / package.json flagged packages\nEncoding: base64 payloads, hex/unicode escapes, string manipulation tricks"
      },
      {
        "title": "References",
        "body": "references/known-patterns.md — catalog of real attack patterns from ClawHub\nreferences/prompt-injection-patterns.md — prompt injection signatures to detect"
      },
      {
        "title": "Important",
        "body": "If a skill scores MEDIUM or above, always show Abidi the full findings before taking any action. Never override or bypass the auditor. This is the last line of defense before untrusted code enters the system."
      }
    ],
    "body": "Skill Auditor\n\nSecurity gatekeeper for third-party skill installation. No skill gets installed without passing audit.\n\nWhen to Use\nBefore installing ANY skill from ClawHub or external sources\nWhen asked to review/evaluate a skill's safety\nWhen clawhub install or similar installation is requested\nAudit Workflow\n1. Quarantine First\n\nNever copy a skill directly to the production skills directory. Always quarantine first:\n\nbash skills/skill-auditor/scripts/quarantine.sh /path/to/skill-source\n\n\nThis copies the skill to a temp directory, runs the full audit, and only allows installation if the risk score is CLEAN or LOW.\n\n2. Manual Audit (Python Script Directly)\n\nFor inspection without the quarantine wrapper:\n\npython3 skills/skill-auditor/scripts/audit_skill.py /path/to/skill-dir\n\n\nOutputs JSON report to stdout. Add --human for formatted text output.\n\n3. Interpreting Results\nRating\tAction\nCLEAN\tSafe to install\nLOW\tSafe, minor notes — review findings briefly\nMEDIUM\tDo NOT install without manual review of each finding\nHIGH\tBlock installation — likely malicious patterns detected\nCRITICAL\tBlock immediately — active threat indicators (exfil, prompt injection, obfuscated payloads)\n4. Exit Codes\n0 = CLEAN or LOW (safe)\n1 = MEDIUM (needs review)\n2 = HIGH or CRITICAL (blocked)\nWhat Gets Scanned\nAll files: inventory, sizes, suspicious file types\nCode: shell commands, network calls, env access, filesystem escape, obfuscation, dynamic imports\nSKILL.md: prompt injection patterns, permission scope requests\nDependencies: requirements.txt / package.json flagged packages\nEncoding: base64 payloads, hex/unicode escapes, string manipulation tricks\nReferences\nreferences/known-patterns.md — catalog of real attack patterns from ClawHub\nreferences/prompt-injection-patterns.md — prompt injection signatures to detect\nImportant\n\nIf a skill scores MEDIUM or above, always show Abidi the full findings before taking any action. Never override or bypass the auditor. This is the last line of defense before untrusted code enters the system."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/aiwithabidi/agxntsix-skill-auditor",
    "publisherUrl": "https://clawhub.ai/aiwithabidi/agxntsix-skill-auditor",
    "owner": "aiwithabidi",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/agxntsix-skill-auditor",
    "downloadUrl": "https://openagent3.xyz/downloads/agxntsix-skill-auditor",
    "agentUrl": "https://openagent3.xyz/skills/agxntsix-skill-auditor/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agxntsix-skill-auditor/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agxntsix-skill-auditor/agent.md"
  }
}