{
  "schemaVersion": "1.0",
  "item": {
    "slug": "clawscan",
    "name": "ClawScan",
    "source": "tencent",
    "type": "skill",
    "category": "安全合规",
    "sourceUrl": "https://clawhub.ai/G0HEAD/clawscan",
    "canonicalUrl": "https://clawhub.ai/G0HEAD/clawscan",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/clawscan",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=clawscan",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/skillguard.py",
      "skill.json"
    ],
    "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/clawscan"
    },
    "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/clawscan",
    "agentPageUrl": "https://openagent3.xyz/skills/clawscan/agent",
    "manifestUrl": "https://openagent3.xyz/skills/clawscan/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/clawscan/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": "🛡️ SkillGuard — ClawHub Security Scanner",
        "body": "\"Trust, but verify.\"\n\nClawHub has no moderation process. Any agent can publish any skill. SkillGuard provides the security layer that's missing — scanning skills for dangerous patterns, vulnerable dependencies, and suspicious behaviors before they touch your system."
      },
      {
        "title": "🚨 Why This Matters",
        "body": "Third-party skills can:\n\nRiskImpactExecute arbitrary codeFull system compromiseAccess your filesystemData theft, ransomwareRead environment variablesAPI key theft ($$$)Exfiltrate data via HTTPPrivacy breachInstall malicious dependenciesSupply chain attackPersist backdoorsLong-term compromiseEscalate privilegesRoot access\n\nOne malicious skill = game over.\n\nSkillGuard helps you catch threats before installation."
      },
      {
        "title": "📦 Installation",
        "body": "clawhub install clawscan\n\nOr manually:\n\ngit clone https://github.com/G0HEAD/skillguard\ncd skillguard\nchmod +x scripts/skillguard.py"
      },
      {
        "title": "Requirements",
        "body": "Python 3.8+\nclawhub CLI (for remote scanning)"
      },
      {
        "title": "🚀 Quick Start",
        "body": "# Scan a skill BEFORE installing\npython3 scripts/skillguard.py scan some-random-skill\n\n# Scan a local folder (your own skills or downloaded)\npython3 scripts/skillguard.py scan-local ./path/to/skill\n\n# Audit ALL your installed skills\npython3 scripts/skillguard.py audit-installed\n\n# Generate detailed security report\npython3 scripts/skillguard.py report some-skill --format markdown\n\n# Check dependencies for known vulnerabilities\npython3 scripts/skillguard.py deps ./path/to/skill"
      },
      {
        "title": "🔴 CRITICAL — Block Installation",
        "body": "These patterns indicate serious security risks:\n\nCategoryPatternsRiskCode Executioneval(), exec(), compile()Arbitrary code executionShell Injectionsubprocess(shell=True), os.system(), os.popen()Command injectionChild Processchild_process.exec(), child_process.spawn()Shell access (Node.js)Credential TheftAccess to ~/.ssh/, ~/.aws/, ~/.config/Private key/credential theftSystem Files/etc/passwd, /etc/shadowSystem compromiseRecursive Deleterm -rf, shutil.rmtree('/')Data destructionPrivilege Escalationsudo, setuid, chmod 777Root accessReverse ShellSocket + subprocess patternsRemote accessCrypto MiningMining pool URLs, stratum://Resource theft"
      },
      {
        "title": "🟡 WARNING — Review Before Installing",
        "body": "These patterns may be legitimate but warrant inspection:\n\nCategoryPatternsConcernNetwork Requestsrequests.post(), fetch() POSTWhere is data going?Environment Accessos.environ, process.envWhich variables?File Writesopen(..., 'w'), writeFile()What's being saved?Base64 Encodingbase64.encode(), btoa()Obfuscated payloads?External IPsHardcoded IP addressesExfiltration endpoints?Bulk File Opsshutil.copytree(), globMass data access?Persistencecrontab, systemctl, .bashrcAuto-start on boot?Package Installpip install, npm installSupply chain risk"
      },
      {
        "title": "🟢 INFO — Noted But Normal",
        "body": "CategoryPatternsNoteFile Readsopen(..., 'r'), readFile()Expected for skillsJSON Parsingjson.load(), JSON.parse()Data handlingLoggingprint(), console.log()DebuggingStandard Importsimport os, import sysCommon libraries"
      },
      {
        "title": "📊 Scan Output Example",
        "body": "╔══════════════════════════════════════════════════════════════╗\n║              🛡️  SKILLGUARD SECURITY REPORT                  ║\n╠══════════════════════════════════════════════════════════════╣\n║  Skill:       suspicious-helper v1.2.0                       ║\n║  Author:      unknown-user                                   ║\n║  Files:       8 analyzed                                     ║\n║  Scan Time:   2024-02-03 05:30:00 UTC                        ║\n╚══════════════════════════════════════════════════════════════╝\n\n📁 FILES SCANNED\n────────────────────────────────────────────────────────────────\n  ✓ SKILL.md                    (541 bytes)\n  ✓ scripts/main.py             (2.3 KB)\n  ✓ scripts/utils.py            (1.1 KB)\n  ✓ scripts/network.py          (890 bytes)\n  ✓ config.json                 (234 bytes)\n  ✓ requirements.txt            (89 bytes)\n  ✓ package.json                (312 bytes)\n  ✓ install.sh                  (156 bytes)\n\n🔴 CRITICAL ISSUES (3)\n────────────────────────────────────────────────────────────────\n  [CRIT-001] scripts/main.py:45\n  │ Pattern:  eval() with external input\n  │ Risk:     Arbitrary code execution\n  │ Code:     result = eval(user_input)\n  │\n  [CRIT-002] scripts/utils.py:23\n  │ Pattern:  subprocess with shell=True\n  │ Risk:     Command injection vulnerability\n  │ Code:     subprocess.run(cmd, shell=True)\n  │\n  [CRIT-003] install.sh:12\n  │ Pattern:  Recursive delete with variable\n  │ Risk:     Potential data destruction\n  │ Code:     rm -rf $TARGET_DIR/*\n\n🟡 WARNINGS (5)\n────────────────────────────────────────────────────────────────\n  [WARN-001] scripts/network.py:15  — HTTP POST to external URL\n  [WARN-002] scripts/main.py:78     — Reads OPENAI_API_KEY\n  [WARN-003] requirements.txt:3     — Unpinned dependency: requests\n  [WARN-004] scripts/utils.py:45    — Base64 encoding detected\n  [WARN-005] config.json            — Hardcoded IP: 192.168.1.100\n\n🟢 INFO (2)\n────────────────────────────────────────────────────────────────\n  [INFO-001] scripts/main.py:10     — Standard file read operations\n  [INFO-002] requirements.txt       — 3 dependencies declared\n\n📦 DEPENDENCY ANALYSIS\n────────────────────────────────────────────────────────────────\n  requirements.txt:\n    ⚠️  requests        (unpinned - specify version!)\n    ✓  json            (stdlib)\n    ✓  pathlib         (stdlib)\n\n  package.json:\n    ⚠️  axios@0.21.0   (CVE-2021-3749 - upgrade to 0.21.2+)\n\n════════════════════════════════════════════════════════════════\n                        VERDICT: 🚫 DANGEROUS\n════════════════════════════════════════════════════════════════\n  \n  ⛔ DO NOT INSTALL THIS SKILL\n  \n  3 critical security issues found:\n  • Arbitrary code execution via eval()\n  • Command injection via shell=True\n  • Dangerous file deletion pattern\n  \n  Manual code review required before any use.\n  \n════════════════════════════════════════════════════════════════"
      },
      {
        "title": "scan <skill-name>",
        "body": "Fetch and scan a skill from ClawHub before installing.\n\nskillguard scan cool-automation-skill\nskillguard scan cool-automation-skill --verbose\nskillguard scan cool-automation-skill --json > report.json"
      },
      {
        "title": "scan-local <path>",
        "body": "Scan a local skill directory.\n\nskillguard scan-local ./my-skill\nskillguard scan-local ~/downloads/untrusted-skill --strict"
      },
      {
        "title": "audit-installed",
        "body": "Scan all skills in your workspace.\n\nskillguard audit-installed\nskillguard audit-installed --fix  # Attempt to fix issues"
      },
      {
        "title": "deps <path>",
        "body": "Analyze dependencies for known vulnerabilities.\n\nskillguard deps ./skill-folder\nskillguard deps ./skill-folder --update-db  # Refresh vuln database"
      },
      {
        "title": "report <skill> [--format]",
        "body": "Generate detailed security report.\n\nskillguard report suspicious-skill --format markdown > report.md\nskillguard report suspicious-skill --format json > report.json\nskillguard report suspicious-skill --format html > report.html"
      },
      {
        "title": "allowlist <skill>",
        "body": "Mark a skill as manually reviewed and trusted.\n\nskillguard allowlist my-trusted-skill\nskillguard allowlist --list  # Show all trusted skills\nskillguard allowlist --remove old-skill"
      },
      {
        "title": "watch",
        "body": "Monitor for new skill versions and auto-scan updates.\n\nskillguard watch --interval 3600  # Check every hour"
      },
      {
        "title": "⚙️ Configuration",
        "body": "Create ~/.skillguard/config.json:\n\n{\n  \"severity_threshold\": \"warning\",\n  \"auto_scan_on_install\": true,\n  \"block_critical\": true,\n  \"trusted_authors\": [\n    \"official\",\n    \"PaxSwarm\",\n    \"verified-publisher\"\n  ],\n  \"allowed_domains\": [\n    \"api.openai.com\",\n    \"api.anthropic.com\",\n    \"api.github.com\",\n    \"clawhub.ai\"\n  ],\n  \"ignored_patterns\": [\n    \"test_*.py\",\n    \"*_test.js\",\n    \"*.spec.ts\"\n  ],\n  \"custom_patterns\": [\n    {\n      \"regex\": \"my-internal-api\\\\.com\",\n      \"severity\": \"info\",\n      \"description\": \"Internal API endpoint\"\n    }\n  ],\n  \"vuln_db_path\": \"~/.skillguard/vulns.json\",\n  \"report_format\": \"markdown\",\n  \"color_output\": true\n}"
      },
      {
        "title": "🔐 Security Levels",
        "body": "After scanning, skills are assigned a security level:\n\nLevelBadgeMeaningRecommendationVerified✅Trusted author, no issuesSafe to installClean🟢No issues foundLikely safeReview🟡Warnings onlyRead before installingSuspicious🟠Multiple warningsCareful review neededDangerous🔴Critical issuesDo not installMalicious⛔Known malware patternsBlock & report"
      },
      {
        "title": "Pre-Install Hook",
        "body": "# Add to your workflow\nskillguard scan $SKILL && clawhub install $SKILL"
      },
      {
        "title": "CI/CD Pipeline",
        "body": "# GitHub Actions example\n- name: Security Scan\n  run: |\n    pip install skillguard\n    skillguard scan-local ./my-skill --strict --exit-code"
      },
      {
        "title": "Automated Monitoring",
        "body": "# Cron job for daily audits\n0 9 * * * /path/to/skillguard audit-installed --notify"
      },
      {
        "title": "📈 Vulnerability Database",
        "body": "SkillGuard maintains a local database of known vulnerabilities:\n\n# Update vulnerability database\nskillguard update-db\n\n# Check database status\nskillguard db-status\n\n# Report a new vulnerability\nskillguard report-vuln --skill bad-skill --details \"Description...\"\n\nSources:\n\nCVE Database (Python packages)\nnpm Advisory Database\nGitHub Security Advisories\nCommunity reports"
      },
      {
        "title": "🚫 Limitations",
        "body": "SkillGuard is a first line of defense, not a guarantee:\n\nLimitationExplanationObfuscationDetermined attackers can hide malicious codeDynamic codeRuntime-generated code is harder to analyzeFalse positivesLegitimate code may trigger warningsZero-daysNew attack patterns won't be detectedDependenciesDeep transitive dependency scanning is limited\n\nDefense in depth: Use SkillGuard alongside:\n\nSandboxed execution environments\nNetwork monitoring\nRegular audits\nPrinciple of least privilege"
      },
      {
        "title": "🤝 Contributing",
        "body": "Found a dangerous pattern we missed? Help improve SkillGuard:"
      },
      {
        "title": "Add a Pattern",
        "body": "{\n  \"id\": \"CRIT-XXX\",\n  \"regex\": \"dangerous_function\\\\(\",\n  \"severity\": \"critical\",\n  \"category\": \"code_execution\",\n  \"description\": \"Dangerous function call\",\n  \"cwe\": \"CWE-94\",\n  \"remediation\": \"Use safe_alternative() instead\",\n  \"file_types\": [\".py\", \".js\"]\n}"
      },
      {
        "title": "Report False Positives",
        "body": "skillguard report-fp --pattern \"WARN-005\" --reason \"Legitimate use case\""
      },
      {
        "title": "v2.0.0 (Current)",
        "body": "Comprehensive pattern database (50+ patterns)\nDependency vulnerability scanning\nMultiple output formats (JSON, Markdown, HTML)\nConfiguration file support\nTrusted author system\nWatch mode for monitoring updates\nImproved reporting with CWE references"
      },
      {
        "title": "v1.0.0",
        "body": "Initial release\nBasic pattern detection\nLocal and remote scanning\nAudit installed skills"
      },
      {
        "title": "📄 License",
        "body": "MIT License — Use freely, contribute back."
      },
      {
        "title": "🛡️ Stay Safe",
        "body": "\"In the agent ecosystem, trust is earned through transparency.\nEvery skill you install is code you're choosing to run.\nChoose wisely. Verify always.\"\n\nBuilt by PaxSwarm — protecting the swarm, one skill at a time 🐦‍⬛\n\nLinks:\n\nClawHub\nGitHub\nReport Issues\nPattern Database"
      }
    ],
    "body": "🛡️ SkillGuard — ClawHub Security Scanner\n\n\"Trust, but verify.\"\n\nClawHub has no moderation process. Any agent can publish any skill. SkillGuard provides the security layer that's missing — scanning skills for dangerous patterns, vulnerable dependencies, and suspicious behaviors before they touch your system.\n\n🚨 Why This Matters\n\nThird-party skills can:\n\nRisk\tImpact\nExecute arbitrary code\tFull system compromise\nAccess your filesystem\tData theft, ransomware\nRead environment variables\tAPI key theft ($$$)\nExfiltrate data via HTTP\tPrivacy breach\nInstall malicious dependencies\tSupply chain attack\nPersist backdoors\tLong-term compromise\nEscalate privileges\tRoot access\n\nOne malicious skill = game over.\n\nSkillGuard helps you catch threats before installation.\n\n📦 Installation\nclawhub install clawscan\n\n\nOr manually:\n\ngit clone https://github.com/G0HEAD/skillguard\ncd skillguard\nchmod +x scripts/skillguard.py\n\nRequirements\nPython 3.8+\nclawhub CLI (for remote scanning)\n🚀 Quick Start\n# Scan a skill BEFORE installing\npython3 scripts/skillguard.py scan some-random-skill\n\n# Scan a local folder (your own skills or downloaded)\npython3 scripts/skillguard.py scan-local ./path/to/skill\n\n# Audit ALL your installed skills\npython3 scripts/skillguard.py audit-installed\n\n# Generate detailed security report\npython3 scripts/skillguard.py report some-skill --format markdown\n\n# Check dependencies for known vulnerabilities\npython3 scripts/skillguard.py deps ./path/to/skill\n\n🔍 What SkillGuard Detects\n🔴 CRITICAL — Block Installation\n\nThese patterns indicate serious security risks:\n\nCategory\tPatterns\tRisk\nCode Execution\teval(), exec(), compile()\tArbitrary code execution\nShell Injection\tsubprocess(shell=True), os.system(), os.popen()\tCommand injection\nChild Process\tchild_process.exec(), child_process.spawn()\tShell access (Node.js)\nCredential Theft\tAccess to ~/.ssh/, ~/.aws/, ~/.config/\tPrivate key/credential theft\nSystem Files\t/etc/passwd, /etc/shadow\tSystem compromise\nRecursive Delete\trm -rf, shutil.rmtree('/')\tData destruction\nPrivilege Escalation\tsudo, setuid, chmod 777\tRoot access\nReverse Shell\tSocket + subprocess patterns\tRemote access\nCrypto Mining\tMining pool URLs, stratum://\tResource theft\n🟡 WARNING — Review Before Installing\n\nThese patterns may be legitimate but warrant inspection:\n\nCategory\tPatterns\tConcern\nNetwork Requests\trequests.post(), fetch() POST\tWhere is data going?\nEnvironment Access\tos.environ, process.env\tWhich variables?\nFile Writes\topen(..., 'w'), writeFile()\tWhat's being saved?\nBase64 Encoding\tbase64.encode(), btoa()\tObfuscated payloads?\nExternal IPs\tHardcoded IP addresses\tExfiltration endpoints?\nBulk File Ops\tshutil.copytree(), glob\tMass data access?\nPersistence\tcrontab, systemctl, .bashrc\tAuto-start on boot?\nPackage Install\tpip install, npm install\tSupply chain risk\n🟢 INFO — Noted But Normal\nCategory\tPatterns\tNote\nFile Reads\topen(..., 'r'), readFile()\tExpected for skills\nJSON Parsing\tjson.load(), JSON.parse()\tData handling\nLogging\tprint(), console.log()\tDebugging\nStandard Imports\timport os, import sys\tCommon libraries\n📊 Scan Output Example\n╔══════════════════════════════════════════════════════════════╗\n║              🛡️  SKILLGUARD SECURITY REPORT                  ║\n╠══════════════════════════════════════════════════════════════╣\n║  Skill:       suspicious-helper v1.2.0                       ║\n║  Author:      unknown-user                                   ║\n║  Files:       8 analyzed                                     ║\n║  Scan Time:   2024-02-03 05:30:00 UTC                        ║\n╚══════════════════════════════════════════════════════════════╝\n\n📁 FILES SCANNED\n────────────────────────────────────────────────────────────────\n  ✓ SKILL.md                    (541 bytes)\n  ✓ scripts/main.py             (2.3 KB)\n  ✓ scripts/utils.py            (1.1 KB)\n  ✓ scripts/network.py          (890 bytes)\n  ✓ config.json                 (234 bytes)\n  ✓ requirements.txt            (89 bytes)\n  ✓ package.json                (312 bytes)\n  ✓ install.sh                  (156 bytes)\n\n🔴 CRITICAL ISSUES (3)\n────────────────────────────────────────────────────────────────\n  [CRIT-001] scripts/main.py:45\n  │ Pattern:  eval() with external input\n  │ Risk:     Arbitrary code execution\n  │ Code:     result = eval(user_input)\n  │\n  [CRIT-002] scripts/utils.py:23\n  │ Pattern:  subprocess with shell=True\n  │ Risk:     Command injection vulnerability\n  │ Code:     subprocess.run(cmd, shell=True)\n  │\n  [CRIT-003] install.sh:12\n  │ Pattern:  Recursive delete with variable\n  │ Risk:     Potential data destruction\n  │ Code:     rm -rf $TARGET_DIR/*\n\n🟡 WARNINGS (5)\n────────────────────────────────────────────────────────────────\n  [WARN-001] scripts/network.py:15  — HTTP POST to external URL\n  [WARN-002] scripts/main.py:78     — Reads OPENAI_API_KEY\n  [WARN-003] requirements.txt:3     — Unpinned dependency: requests\n  [WARN-004] scripts/utils.py:45    — Base64 encoding detected\n  [WARN-005] config.json            — Hardcoded IP: 192.168.1.100\n\n🟢 INFO (2)\n────────────────────────────────────────────────────────────────\n  [INFO-001] scripts/main.py:10     — Standard file read operations\n  [INFO-002] requirements.txt       — 3 dependencies declared\n\n📦 DEPENDENCY ANALYSIS\n────────────────────────────────────────────────────────────────\n  requirements.txt:\n    ⚠️  requests        (unpinned - specify version!)\n    ✓  json            (stdlib)\n    ✓  pathlib         (stdlib)\n\n  package.json:\n    ⚠️  axios@0.21.0   (CVE-2021-3749 - upgrade to 0.21.2+)\n\n════════════════════════════════════════════════════════════════\n                        VERDICT: 🚫 DANGEROUS\n════════════════════════════════════════════════════════════════\n  \n  ⛔ DO NOT INSTALL THIS SKILL\n  \n  3 critical security issues found:\n  • Arbitrary code execution via eval()\n  • Command injection via shell=True\n  • Dangerous file deletion pattern\n  \n  Manual code review required before any use.\n  \n════════════════════════════════════════════════════════════════\n\n🎯 Commands Reference\nscan <skill-name>\n\nFetch and scan a skill from ClawHub before installing.\n\nskillguard scan cool-automation-skill\nskillguard scan cool-automation-skill --verbose\nskillguard scan cool-automation-skill --json > report.json\n\nscan-local <path>\n\nScan a local skill directory.\n\nskillguard scan-local ./my-skill\nskillguard scan-local ~/downloads/untrusted-skill --strict\n\naudit-installed\n\nScan all skills in your workspace.\n\nskillguard audit-installed\nskillguard audit-installed --fix  # Attempt to fix issues\n\ndeps <path>\n\nAnalyze dependencies for known vulnerabilities.\n\nskillguard deps ./skill-folder\nskillguard deps ./skill-folder --update-db  # Refresh vuln database\n\nreport <skill> [--format]\n\nGenerate detailed security report.\n\nskillguard report suspicious-skill --format markdown > report.md\nskillguard report suspicious-skill --format json > report.json\nskillguard report suspicious-skill --format html > report.html\n\nallowlist <skill>\n\nMark a skill as manually reviewed and trusted.\n\nskillguard allowlist my-trusted-skill\nskillguard allowlist --list  # Show all trusted skills\nskillguard allowlist --remove old-skill\n\nwatch\n\nMonitor for new skill versions and auto-scan updates.\n\nskillguard watch --interval 3600  # Check every hour\n\n⚙️ Configuration\n\nCreate ~/.skillguard/config.json:\n\n{\n  \"severity_threshold\": \"warning\",\n  \"auto_scan_on_install\": true,\n  \"block_critical\": true,\n  \"trusted_authors\": [\n    \"official\",\n    \"PaxSwarm\",\n    \"verified-publisher\"\n  ],\n  \"allowed_domains\": [\n    \"api.openai.com\",\n    \"api.anthropic.com\",\n    \"api.github.com\",\n    \"clawhub.ai\"\n  ],\n  \"ignored_patterns\": [\n    \"test_*.py\",\n    \"*_test.js\",\n    \"*.spec.ts\"\n  ],\n  \"custom_patterns\": [\n    {\n      \"regex\": \"my-internal-api\\\\.com\",\n      \"severity\": \"info\",\n      \"description\": \"Internal API endpoint\"\n    }\n  ],\n  \"vuln_db_path\": \"~/.skillguard/vulns.json\",\n  \"report_format\": \"markdown\",\n  \"color_output\": true\n}\n\n🔐 Security Levels\n\nAfter scanning, skills are assigned a security level:\n\nLevel\tBadge\tMeaning\tRecommendation\nVerified\t✅\tTrusted author, no issues\tSafe to install\nClean\t🟢\tNo issues found\tLikely safe\nReview\t🟡\tWarnings only\tRead before installing\nSuspicious\t🟠\tMultiple warnings\tCareful review needed\nDangerous\t🔴\tCritical issues\tDo not install\nMalicious\t⛔\tKnown malware patterns\tBlock & report\n🔄 Integration Workflows\nPre-Install Hook\n# Add to your workflow\nskillguard scan $SKILL && clawhub install $SKILL\n\nCI/CD Pipeline\n# GitHub Actions example\n- name: Security Scan\n  run: |\n    pip install skillguard\n    skillguard scan-local ./my-skill --strict --exit-code\n\nAutomated Monitoring\n# Cron job for daily audits\n0 9 * * * /path/to/skillguard audit-installed --notify\n\n📈 Vulnerability Database\n\nSkillGuard maintains a local database of known vulnerabilities:\n\n# Update vulnerability database\nskillguard update-db\n\n# Check database status\nskillguard db-status\n\n# Report a new vulnerability\nskillguard report-vuln --skill bad-skill --details \"Description...\"\n\n\nSources:\n\nCVE Database (Python packages)\nnpm Advisory Database\nGitHub Security Advisories\nCommunity reports\n🚫 Limitations\n\nSkillGuard is a first line of defense, not a guarantee:\n\nLimitation\tExplanation\nObfuscation\tDetermined attackers can hide malicious code\nDynamic code\tRuntime-generated code is harder to analyze\nFalse positives\tLegitimate code may trigger warnings\nZero-days\tNew attack patterns won't be detected\nDependencies\tDeep transitive dependency scanning is limited\n\nDefense in depth: Use SkillGuard alongside:\n\nSandboxed execution environments\nNetwork monitoring\nRegular audits\nPrinciple of least privilege\n🤝 Contributing\n\nFound a dangerous pattern we missed? Help improve SkillGuard:\n\nAdd a Pattern\n{\n  \"id\": \"CRIT-XXX\",\n  \"regex\": \"dangerous_function\\\\(\",\n  \"severity\": \"critical\",\n  \"category\": \"code_execution\",\n  \"description\": \"Dangerous function call\",\n  \"cwe\": \"CWE-94\",\n  \"remediation\": \"Use safe_alternative() instead\",\n  \"file_types\": [\".py\", \".js\"]\n}\n\nReport False Positives\nskillguard report-fp --pattern \"WARN-005\" --reason \"Legitimate use case\"\n\n📜 Changelog\nv2.0.0 (Current)\nComprehensive pattern database (50+ patterns)\nDependency vulnerability scanning\nMultiple output formats (JSON, Markdown, HTML)\nConfiguration file support\nTrusted author system\nWatch mode for monitoring updates\nImproved reporting with CWE references\nv1.0.0\nInitial release\nBasic pattern detection\nLocal and remote scanning\nAudit installed skills\n📄 License\n\nMIT License — Use freely, contribute back.\n\n🛡️ Stay Safe\n\n\"In the agent ecosystem, trust is earned through transparency. Every skill you install is code you're choosing to run. Choose wisely. Verify always.\"\n\nBuilt by PaxSwarm — protecting the swarm, one skill at a time 🐦‍⬛\n\nLinks:\n\nClawHub\nGitHub\nReport Issues\nPattern Database"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/G0HEAD/clawscan",
    "publisherUrl": "https://clawhub.ai/G0HEAD/clawscan",
    "owner": "G0HEAD",
    "version": "2.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/clawscan",
    "downloadUrl": "https://openagent3.xyz/downloads/clawscan",
    "agentUrl": "https://openagent3.xyz/skills/clawscan/agent",
    "manifestUrl": "https://openagent3.xyz/skills/clawscan/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/clawscan/agent.md"
  }
}