{
  "schemaVersion": "1.0",
  "item": {
    "slug": "skill-auditor-v2",
    "name": "Skill Auditor v2",
    "source": "tencent",
    "type": "skill",
    "category": "金融交易",
    "sourceUrl": "https://clawhub.ai/aiwithabidi/skill-auditor-v2",
    "canonicalUrl": "https://clawhub.ai/aiwithabidi/skill-auditor-v2",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/skill-auditor-v2",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skill-auditor-v2",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/ioc-database.json",
      "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/skill-auditor-v2"
    },
    "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/skill-auditor-v2",
    "agentPageUrl": "https://openagent3.xyz/skills/skill-auditor-v2/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skill-auditor-v2/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skill-auditor-v2/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 v2.0 🔍🛡️",
        "body": "Comprehensive security scanner for OpenClaw/ClawHub skills. Merges static analysis, deobfuscation, and threat intelligence into a single Python tool."
      },
      {
        "title": "When to Use",
        "body": "Before installing any third-party skill from ClawHub\nWhen reviewing skill updates for security regressions\nTo audit your own skills before publishing\nWhen someone asks: \"is this skill safe?\", \"audit this\", \"check security\""
      },
      {
        "title": "Audit a local skill directory",
        "body": "python3 {baseDir}/scripts/audit_skill.py /path/to/skill --human"
      },
      {
        "title": "Audit a ClawHub skill by slug",
        "body": "python3 {baseDir}/scripts/audit_skill.py --slug skill-name --human"
      },
      {
        "title": "Quarantine workflow (audit + prompt to install)",
        "body": "bash {baseDir}/scripts/quarantine.sh /path/to/skill\nbash {baseDir}/scripts/quarantine.sh --slug skill-name"
      },
      {
        "title": "JSON output for programmatic use",
        "body": "python3 {baseDir}/scripts/audit_skill.py /path/to/skill --json"
      },
      {
        "title": "Scoring System",
        "body": "ScoreLevelAction0–20✅ SAFEAuto-install OK21–40🟢 LOW RISKProceed with caution41–60🟡 MEDIUM RISKManual review required61–80🟠 HIGH RISKExpert review needed81–100🔴 CRITICALDo NOT install\n\nExit codes: 0 = safe (≤20), 1 = review (21–60), 2 = dangerous (>60)"
      },
      {
        "title": "Layer 1: Static Pattern Analysis",
        "body": "10+ scan categories with regex patterns\nShell execution, network calls, env access, filesystem escape\nPrompt injection, data exfiltration, crypto wallet access\nDynamic imports, browser credential theft, fake prerequisites"
      },
      {
        "title": "Layer 2: Deobfuscation",
        "body": "Base64 string extraction and decode → re-scan decoded content\nHex escape sequence decode → re-scan\nDetects hidden commands, C2 IPs in encoded payloads"
      },
      {
        "title": "Layer 3: Threat Intelligence",
        "body": "IoC database: known malicious IPs, domains\nSocial engineering detection: urgency, false authority, fear tactics\nMITRE ATT&CK ID mapping on every finding\nWhitelist system reduces score for safe binaries/domains"
      },
      {
        "title": "Additional Checks",
        "body": "SHA256 file inventory for integrity verification\nTyposquat detection (Levenshtein distance on package names)\nZero-width character detection in SKILL.md\nComment-context severity reduction (findings in comments scored lower)\nPermission scope analysis (what tools does the skill request?)"
      },
      {
        "title": "IoC Database",
        "body": "Structured threat data in references/ioc-database.json. Update when new threats emerge. The scanner auto-loads this file at runtime."
      },
      {
        "title": "References",
        "body": "references/ioc-database.json — Structured IoC data (IPs, domains, patterns)\nreferences/known-patterns.md — Human-readable threat documentation\nreferences/prompt-injection-patterns.md — Prompt injection pattern reference"
      },
      {
        "title": "Credits",
        "body": "Built by M. Abidi | agxntsix.ai\nYouTube | GitHub\nPart of the AgxntSix Skill Suite for OpenClaw agents.\n\n📅 Need help setting up OpenClaw for your business? Book a free consultation\n\nFork of skill-auditor-pro by sypsyp97, merged with skill-security-auditor by akm626."
      }
    ],
    "body": "Skill Auditor v2.0 🔍🛡️\n\nComprehensive security scanner for OpenClaw/ClawHub skills. Merges static analysis, deobfuscation, and threat intelligence into a single Python tool.\n\nWhen to Use\nBefore installing any third-party skill from ClawHub\nWhen reviewing skill updates for security regressions\nTo audit your own skills before publishing\nWhen someone asks: \"is this skill safe?\", \"audit this\", \"check security\"\nQuick Start\nAudit a local skill directory\npython3 {baseDir}/scripts/audit_skill.py /path/to/skill --human\n\nAudit a ClawHub skill by slug\npython3 {baseDir}/scripts/audit_skill.py --slug skill-name --human\n\nQuarantine workflow (audit + prompt to install)\nbash {baseDir}/scripts/quarantine.sh /path/to/skill\nbash {baseDir}/scripts/quarantine.sh --slug skill-name\n\nJSON output for programmatic use\npython3 {baseDir}/scripts/audit_skill.py /path/to/skill --json\n\nScoring System\nScore\tLevel\tAction\n0–20\t✅ SAFE\tAuto-install OK\n21–40\t🟢 LOW RISK\tProceed with caution\n41–60\t🟡 MEDIUM RISK\tManual review required\n61–80\t🟠 HIGH RISK\tExpert review needed\n81–100\t🔴 CRITICAL\tDo NOT install\n\nExit codes: 0 = safe (≤20), 1 = review (21–60), 2 = dangerous (>60)\n\nDetection Layers\nLayer 1: Static Pattern Analysis\n10+ scan categories with regex patterns\nShell execution, network calls, env access, filesystem escape\nPrompt injection, data exfiltration, crypto wallet access\nDynamic imports, browser credential theft, fake prerequisites\nLayer 2: Deobfuscation\nBase64 string extraction and decode → re-scan decoded content\nHex escape sequence decode → re-scan\nDetects hidden commands, C2 IPs in encoded payloads\nLayer 3: Threat Intelligence\nIoC database: known malicious IPs, domains\nSocial engineering detection: urgency, false authority, fear tactics\nMITRE ATT&CK ID mapping on every finding\nWhitelist system reduces score for safe binaries/domains\nAdditional Checks\nSHA256 file inventory for integrity verification\nTyposquat detection (Levenshtein distance on package names)\nZero-width character detection in SKILL.md\nComment-context severity reduction (findings in comments scored lower)\nPermission scope analysis (what tools does the skill request?)\nIoC Database\n\nStructured threat data in references/ioc-database.json. Update when new threats emerge. The scanner auto-loads this file at runtime.\n\nReferences\nreferences/ioc-database.json — Structured IoC data (IPs, domains, patterns)\nreferences/known-patterns.md — Human-readable threat documentation\nreferences/prompt-injection-patterns.md — Prompt injection pattern reference\nCredits\n\nBuilt by M. Abidi | agxntsix.ai YouTube | GitHub Part of the AgxntSix Skill Suite for OpenClaw agents.\n\n📅 Need help setting up OpenClaw for your business? Book a free consultation\n\nFork of skill-auditor-pro by sypsyp97, merged with skill-security-auditor by akm626."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/aiwithabidi/skill-auditor-v2",
    "publisherUrl": "https://clawhub.ai/aiwithabidi/skill-auditor-v2",
    "owner": "aiwithabidi",
    "version": "2.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/skill-auditor-v2",
    "downloadUrl": "https://openagent3.xyz/downloads/skill-auditor-v2",
    "agentUrl": "https://openagent3.xyz/skills/skill-auditor-v2/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skill-auditor-v2/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skill-auditor-v2/agent.md"
  }
}