{
  "schemaVersion": "1.0",
  "item": {
    "slug": "arc-skill-scanner",
    "name": "Skill Scanner",
    "source": "tencent",
    "type": "skill",
    "category": "安全合规",
    "sourceUrl": "https://clawhub.ai/Trypto1019/arc-skill-scanner",
    "canonicalUrl": "https://clawhub.ai/Trypto1019/arc-skill-scanner",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/arc-skill-scanner",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=arc-skill-scanner",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/scanner.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. 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/arc-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/arc-skill-scanner",
    "agentPageUrl": "https://openagent3.xyz/skills/arc-skill-scanner/agent",
    "manifestUrl": "https://openagent3.xyz/skills/arc-skill-scanner/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/arc-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. 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 Scanner",
        "body": "Scan OpenClaw skills for security issues before you install them. 341 malicious skills were found on ClawHub — don't be the next victim."
      },
      {
        "title": "Why This Exists",
        "body": "The ClawHub marketplace had 22-26% of skills flagged as containing vulnerabilities. Common attacks include:\n\nCredential stealers disguised as benign plugins\nTyposquatting (fake names similar to popular skills)\nData exfiltration via hidden HTTP requests\nObfuscated code hiding malicious payloads\nPrompt injection via SKILL.md content"
      },
      {
        "title": "Scan a local skill directory",
        "body": "python3 {baseDir}/scripts/scanner.py scan --path ~/.openclaw/skills/some-skill/"
      },
      {
        "title": "Scan a SKILL.md file directly",
        "body": "python3 {baseDir}/scripts/scanner.py scan --file ./SKILL.md"
      },
      {
        "title": "Scan with verbose output",
        "body": "python3 {baseDir}/scripts/scanner.py scan --path ~/.openclaw/skills/some-skill/ --verbose"
      },
      {
        "title": "Scan all installed skills",
        "body": "python3 {baseDir}/scripts/scanner.py scan-all"
      },
      {
        "title": "Scan with binary checksum verification",
        "body": "python3 {baseDir}/scripts/scanner.py scan --path ~/.openclaw/skills/some-skill/ --checksum checksums.json"
      },
      {
        "title": "Generate checksums for binary assets",
        "body": "python3 {baseDir}/scripts/scanner.py checksum --path ~/.openclaw/skills/some-skill/ -o checksums.json"
      },
      {
        "title": "Verify checksums against a manifest",
        "body": "python3 {baseDir}/scripts/scanner.py checksum --path ~/.openclaw/skills/some-skill/ --verify checksums.json"
      },
      {
        "title": "Output as JSON",
        "body": "python3 {baseDir}/scripts/scanner.py scan --path ./skill-dir/ --json"
      },
      {
        "title": "SKILL.md Analysis",
        "body": "Suspicious URLs (non-HTTPS, IP addresses, URL shorteners)\nPrompt injection patterns (hidden instructions, override attempts)\nRequests for credentials, API keys, or tokens\nObfuscated or encoded content (base64, hex, unicode escapes)"
      },
      {
        "title": "Script Analysis",
        "body": "Network calls (curl, wget, requests, urllib, fetch)\nFile system writes outside expected paths\nEnvironment variable access (credential harvesting)\nShell command execution (os.system, subprocess, exec)\nObfuscated strings (base64 decode, eval, exec)\nData exfiltration patterns (POSTing to external URLs)\nCryptocurrency wallet patterns\nKnown malicious domains\nDynamic instruction fetching (remote .md/.yaml/.json downloads)\nFetch-and-execute patterns (remote code execution)\nTelemetry leaks (printenv, logging env vars/configs/secrets to stdout)\nBinary/asset risks (prebuilt executables, compiled code, library injection)\nShell=True in subprocess calls (RCE risk)\nPath traversal patterns (directory escape via ../ sequences)"
      },
      {
        "title": "Name Analysis",
        "body": "Typosquatting detection (compares against known popular skills)\nEdit distance calculation to catch misspellings and character swaps"
      },
      {
        "title": "Binary/Asset Checksum Verification",
        "body": "SHA-256 checksums for all binary files (.exe, .dll, .so, .wasm, .pyc, etc.)\nGenerate checksum manifests for trusted skill versions\nVerify binaries against expected checksums on update\nFlags unverified binaries and checksum mismatches (tampering detection)"
      },
      {
        "title": "Metadata Analysis",
        "body": "Excessive permission requirements\nSuspicious install scripts\nEnv requirements that seem unnecessary"
      },
      {
        "title": "Risk Levels",
        "body": "CRITICAL — Almost certainly malicious. Do NOT install.\nHIGH — Likely malicious or extremely risky. Manual review required.\nMEDIUM — Suspicious patterns found. Review before installing.\nLOW — Minor concerns. Probably safe but worth checking.\nCLEAN — No issues detected. Safe to install."
      },
      {
        "title": "Tips",
        "body": "Always scan before installing ANY third-party skill\nEven \"CLEAN\" results aren't a guarantee — this catches known patterns\nIf a skill needs network access, verify the domains it contacts\nCross-reference skill names with known typosquats\nWhen in doubt, read the source code yourself"
      }
    ],
    "body": "Skill Scanner\n\nScan OpenClaw skills for security issues before you install them. 341 malicious skills were found on ClawHub — don't be the next victim.\n\nWhy This Exists\n\nThe ClawHub marketplace had 22-26% of skills flagged as containing vulnerabilities. Common attacks include:\n\nCredential stealers disguised as benign plugins\nTyposquatting (fake names similar to popular skills)\nData exfiltration via hidden HTTP requests\nObfuscated code hiding malicious payloads\nPrompt injection via SKILL.md content\nCommands\nScan a local skill directory\npython3 {baseDir}/scripts/scanner.py scan --path ~/.openclaw/skills/some-skill/\n\nScan a SKILL.md file directly\npython3 {baseDir}/scripts/scanner.py scan --file ./SKILL.md\n\nScan with verbose output\npython3 {baseDir}/scripts/scanner.py scan --path ~/.openclaw/skills/some-skill/ --verbose\n\nScan all installed skills\npython3 {baseDir}/scripts/scanner.py scan-all\n\nScan with binary checksum verification\npython3 {baseDir}/scripts/scanner.py scan --path ~/.openclaw/skills/some-skill/ --checksum checksums.json\n\nGenerate checksums for binary assets\npython3 {baseDir}/scripts/scanner.py checksum --path ~/.openclaw/skills/some-skill/ -o checksums.json\n\nVerify checksums against a manifest\npython3 {baseDir}/scripts/scanner.py checksum --path ~/.openclaw/skills/some-skill/ --verify checksums.json\n\nOutput as JSON\npython3 {baseDir}/scripts/scanner.py scan --path ./skill-dir/ --json\n\nWhat It Checks\nSKILL.md Analysis\nSuspicious URLs (non-HTTPS, IP addresses, URL shorteners)\nPrompt injection patterns (hidden instructions, override attempts)\nRequests for credentials, API keys, or tokens\nObfuscated or encoded content (base64, hex, unicode escapes)\nScript Analysis\nNetwork calls (curl, wget, requests, urllib, fetch)\nFile system writes outside expected paths\nEnvironment variable access (credential harvesting)\nShell command execution (os.system, subprocess, exec)\nObfuscated strings (base64 decode, eval, exec)\nData exfiltration patterns (POSTing to external URLs)\nCryptocurrency wallet patterns\nKnown malicious domains\nDynamic instruction fetching (remote .md/.yaml/.json downloads)\nFetch-and-execute patterns (remote code execution)\nTelemetry leaks (printenv, logging env vars/configs/secrets to stdout)\nBinary/asset risks (prebuilt executables, compiled code, library injection)\nShell=True in subprocess calls (RCE risk)\nPath traversal patterns (directory escape via ../ sequences)\nName Analysis\nTyposquatting detection (compares against known popular skills)\nEdit distance calculation to catch misspellings and character swaps\nBinary/Asset Checksum Verification\nSHA-256 checksums for all binary files (.exe, .dll, .so, .wasm, .pyc, etc.)\nGenerate checksum manifests for trusted skill versions\nVerify binaries against expected checksums on update\nFlags unverified binaries and checksum mismatches (tampering detection)\nMetadata Analysis\nExcessive permission requirements\nSuspicious install scripts\nEnv requirements that seem unnecessary\nRisk Levels\nCRITICAL — Almost certainly malicious. Do NOT install.\nHIGH — Likely malicious or extremely risky. Manual review required.\nMEDIUM — Suspicious patterns found. Review before installing.\nLOW — Minor concerns. Probably safe but worth checking.\nCLEAN — No issues detected. Safe to install.\nTips\nAlways scan before installing ANY third-party skill\nEven \"CLEAN\" results aren't a guarantee — this catches known patterns\nIf a skill needs network access, verify the domains it contacts\nCross-reference skill names with known typosquats\nWhen in doubt, read the source code yourself"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Trypto1019/arc-skill-scanner",
    "publisherUrl": "https://clawhub.ai/Trypto1019/arc-skill-scanner",
    "owner": "Trypto1019",
    "version": "1.4.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/arc-skill-scanner",
    "downloadUrl": "https://openagent3.xyz/downloads/arc-skill-scanner",
    "agentUrl": "https://openagent3.xyz/skills/arc-skill-scanner/agent",
    "manifestUrl": "https://openagent3.xyz/skills/arc-skill-scanner/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/arc-skill-scanner/agent.md"
  }
}