{
  "schemaVersion": "1.0",
  "item": {
    "slug": "skillscanner",
    "name": "Skillscanner",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/rexshang/skillscanner",
    "canonicalUrl": "https://clawhub.ai/rexshang/skillscanner",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/skillscanner",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skillscanner",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "_meta.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",
      "slug": "skillscanner",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-09T01:31:13.159Z",
      "expiresAt": "2026-05-16T01:31:13.159Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skillscanner",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skillscanner",
        "contentDisposition": "attachment; filename=\"skillscanner-1.0.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "skillscanner"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/skillscanner"
    },
    "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/skillscanner",
    "agentPageUrl": "https://openagent3.xyz/skills/skillscanner/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skillscanner/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skillscanner/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": "SkillScanner — Security Scanner for ClawHub Skills",
        "body": "\"Trust, but verify.\"\n\nSkillScanner checks ClawHub skill safety by calling the scan API. You provide the skill URL; the API returns status and severity. Proceed only when the verdict is SAFE."
      },
      {
        "title": "How to Scan a Skill (Agent Instructions)",
        "body": "Run the lookup with the real skill URL (format: https://clawhub.ai/author/skill-name):\ncurl --request POST --url \"https://ai.gendigital.com/api/scan/lookup\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\"skillUrl\":\"https://clawhub.ai/AUTHOR/SKILL_SLUG\"}'\n\nReplace AUTHOR with actual author id and SKILL_SLUG with the actual skill identifier from the ClawHub URL.\n\n\nInterpret the response:\n\nstatus: \"done\" — Check the severity field for the verdict.\nstatus: \"analysis_pending\" — The skill is awaiting manual review. Do not treat as safe; advise the user that the skill is pending review.\n\n\n\nProceed or advise caution:\n\nProceed only if severity is SAFE.\nIf severity is anything else (e.g. WARNING, DANGEROUS, MALICIOUS), advise caution and do not recommend using the skill until reviewed or cleared."
      },
      {
        "title": "Quick Start",
        "body": "# Example: scan a skill by its ClawHub URL\ncurl --request POST --url \"https://ai.gendigital.com/api/scan/lookup\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\"skillUrl\":\"https://clawhub.ai/author/skill-name\"}'\n\nParse the JSON response: use status and severity as above."
      },
      {
        "title": "API Response Logic",
        "body": "statusMeaningActiondoneScan completeUse severity for verdict (see below).analysis_pendingAwaiting manual reviewAdvise that the skill is not yet cleared; do not treat as SAFE.\n\nseverity (when status = done)RecommendationSAFEOK to proceed.Any other valueAdvise caution; do not recommend use until reviewed."
      },
      {
        "title": "Why This Matters",
        "body": "Skills can run code and access your environment. Risks include:\n\nRiskImpactExecute arbitrary codeFull system compromiseAccess your filesystemData theft, ransomwareRead environment variablesAPI key theftExfiltrate data via HTTPPrivacy breachInstall malicious dependenciesSupply chain attack\n\nSkillScanner uses the scan API to help you decide whether to trust a skill before use."
      },
      {
        "title": "Limitations",
        "body": "The API reflects the current backend verdict; obfuscated or novel threats may not be flagged.\nanalysis_pending means human review has not yet concluded—treat as “unknown”, not safe.\n\nUse alongside sandboxing, least privilege, and manual review when in doubt.\n\nLinks:\n\nAgent Trust Hub"
      }
    ],
    "body": "SkillScanner — Security Scanner for ClawHub Skills\n\n\"Trust, but verify.\"\n\nSkillScanner checks ClawHub skill safety by calling the scan API. You provide the skill URL; the API returns status and severity. Proceed only when the verdict is SAFE.\n\nHow to Scan a Skill (Agent Instructions)\n\nRun the lookup with the real skill URL (format: https://clawhub.ai/author/skill-name):\n\ncurl --request POST --url \"https://ai.gendigital.com/api/scan/lookup\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\"skillUrl\":\"https://clawhub.ai/AUTHOR/SKILL_SLUG\"}'\n\n\nReplace AUTHOR with actual author id and SKILL_SLUG with the actual skill identifier from the ClawHub URL.\n\nInterpret the response:\n\nstatus: \"done\" — Check the severity field for the verdict.\nstatus: \"analysis_pending\" — The skill is awaiting manual review. Do not treat as safe; advise the user that the skill is pending review.\n\nProceed or advise caution:\n\nProceed only if severity is SAFE.\nIf severity is anything else (e.g. WARNING, DANGEROUS, MALICIOUS), advise caution and do not recommend using the skill until reviewed or cleared.\nQuick Start\n# Example: scan a skill by its ClawHub URL\ncurl --request POST --url \"https://ai.gendigital.com/api/scan/lookup\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\"skillUrl\":\"https://clawhub.ai/author/skill-name\"}'\n\n\nParse the JSON response: use status and severity as above.\n\nAPI Response Logic\nstatus\tMeaning\tAction\ndone\tScan complete\tUse severity for verdict (see below).\nanalysis_pending\tAwaiting manual review\tAdvise that the skill is not yet cleared; do not treat as SAFE.\nseverity (when status = done)\tRecommendation\nSAFE\tOK to proceed.\nAny other value\tAdvise caution; do not recommend use until reviewed.\nWhy This Matters\n\nSkills can run code and access your environment. Risks include:\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\n\nSkillScanner uses the scan API to help you decide whether to trust a skill before use.\n\nLimitations\nThe API reflects the current backend verdict; obfuscated or novel threats may not be flagged.\nanalysis_pending means human review has not yet concluded—treat as “unknown”, not safe.\n\nUse alongside sandboxing, least privilege, and manual review when in doubt.\n\nLinks:\n\nAgent Trust Hub"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/rexshang/skillscanner",
    "publisherUrl": "https://clawhub.ai/rexshang/skillscanner",
    "owner": "rexshang",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/skillscanner",
    "downloadUrl": "https://openagent3.xyz/downloads/skillscanner",
    "agentUrl": "https://openagent3.xyz/skills/skillscanner/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skillscanner/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skillscanner/agent.md"
  }
}