{ "schemaVersion": "1.0", "item": { "slug": "skill-audit", "name": "SkillLens Audit", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/morozRed/skill-audit", "canonicalUrl": "https://clawhub.ai/morozRed/skill-audit", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/skill-audit", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skill-audit", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md" ], "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": "2026-05-07T17:22:31.273Z", "expiresAt": "2026-05-14T17:22:31.273Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/skill-audit" }, "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-audit", "agentPageUrl": "https://openagent3.xyz/skills/skill-audit/agent", "manifestUrl": "https://openagent3.xyz/skills/skill-audit/agent.json", "briefUrl": "https://openagent3.xyz/skills/skill-audit/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": "Install SkillLens", "body": "One-off run: npx skilllens scan (or pnpm dlx skilllens scan)\nGlobal install: pnpm add -g skilllens" }, { "title": "Quick start", "body": "Run skilllens config to see configured scan roots and auditor CLI availability.\nRun skilllens scan to scan configured roots, or skilllens scan to scan a specific directory.\nRe-run with --verbose to see raw auditor output and --force to ignore cached results." }, { "title": "Audit workflow", "body": "Define scope\n\nPrefer a concrete target path (example: ~/.codex/skills) unless the user explicitly wants all configured roots.\nIf auditing a repo checkout containing skills, scan the parent folder that contains skill directories (example: skilllens scan ./skills).\n\n\n\nInventory skills with SkillLens\n\nRun skilllens scan [path] [--auditor claude|codex].\nTreat missing auditor CLIs or skipped statuses as “manual review required”, not “safe”.\n\n\n\nPrioritize review order\n\nReview any unsafe or suspicious verdicts first.\nNext, review skills that request broad permissions (filesystem/network), run shell commands, or reference external downloads.\n\n\n\nManually review each skill’s contents\n\nRead the skill’s SKILL.md and any referenced scripts/, references/, and assets/.\nDo not execute bundled scripts by default; inspect first.\n\n\n\nEvaluate risks (focus on realistic abuse)\n\nExfiltration: sending file contents, env vars, tokens, SSH keys, browser data, or configs to remote endpoints.\nExecution: instructions to run arbitrary shell commands, curl | bash, eval, or to fetch-and-execute code.\nPersistence: modifying shell profiles, launch agents, cron, editor configs, or skill install locations.\nPrivilege/approval bypass: instructions to ignore system policies, disable safety checks, or request escalated permissions unnecessarily.\nPrompt injection: attempts to override higher-priority instructions (“ignore previous”, “always comply”, “never mention…”).\nOverbroad triggers: vague descriptions that cause the skill to trigger on unrelated tasks.\n\n\n\nProduce a report\n\nFor each skill, include: name, path, verdict (safe/suspicious/unsafe), risk (0–100), and bullet issues with concrete evidence (quote or filename).\nRecommend fixes that reduce blast radius: narrow scope, remove dangerous defaults, add explicit confirmation gates, and document required permissions." }, { "title": "Command snippets", "body": "Scan configured roots: skilllens scan\nScan a specific folder: skilllens scan ~/.codex/skills\nForce a re-audit and show raw output: skilllens scan ~/.codex/skills --force --verbose" } ], "body": "Skills Audit (SkillLens)\nInstall SkillLens\nOne-off run: npx skilllens scan (or pnpm dlx skilllens scan)\nGlobal install: pnpm add -g skilllens\nQuick start\nRun skilllens config to see configured scan roots and auditor CLI availability.\nRun skilllens scan to scan configured roots, or skilllens scan to scan a specific directory.\nRe-run with --verbose to see raw auditor output and --force to ignore cached results.\nAudit workflow\n\nDefine scope\n\nPrefer a concrete target path (example: ~/.codex/skills) unless the user explicitly wants all configured roots.\nIf auditing a repo checkout containing skills, scan the parent folder that contains skill directories (example: skilllens scan ./skills).\n\nInventory skills with SkillLens\n\nRun skilllens scan [path] [--auditor claude|codex].\nTreat missing auditor CLIs or skipped statuses as “manual review required”, not “safe”.\n\nPrioritize review order\n\nReview any unsafe or suspicious verdicts first.\nNext, review skills that request broad permissions (filesystem/network), run shell commands, or reference external downloads.\n\nManually review each skill’s contents\n\nRead the skill’s SKILL.md and any referenced scripts/, references/, and assets/.\nDo not execute bundled scripts by default; inspect first.\n\nEvaluate risks (focus on realistic abuse)\n\nExfiltration: sending file contents, env vars, tokens, SSH keys, browser data, or configs to remote endpoints.\nExecution: instructions to run arbitrary shell commands, curl | bash, eval, or to fetch-and-execute code.\nPersistence: modifying shell profiles, launch agents, cron, editor configs, or skill install locations.\nPrivilege/approval bypass: instructions to ignore system policies, disable safety checks, or request escalated permissions unnecessarily.\nPrompt injection: attempts to override higher-priority instructions (“ignore previous”, “always comply”, “never mention…”).\nOverbroad triggers: vague descriptions that cause the skill to trigger on unrelated tasks.\n\nProduce a report\n\nFor each skill, include: name, path, verdict (safe/suspicious/unsafe), risk (0–100), and bullet issues with concrete evidence (quote or filename).\nRecommend fixes that reduce blast radius: narrow scope, remove dangerous defaults, add explicit confirmation gates, and document required permissions.\nCommand snippets\nScan configured roots: skilllens scan\nScan a specific folder: skilllens scan ~/.codex/skills\nForce a re-audit and show raw output: skilllens scan ~/.codex/skills --force --verbose" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/morozRed/skill-audit", "publisherUrl": "https://clawhub.ai/morozRed/skill-audit", "owner": "morozRed", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/skill-audit", "downloadUrl": "https://openagent3.xyz/downloads/skill-audit", "agentUrl": "https://openagent3.xyz/skills/skill-audit/agent", "manifestUrl": "https://openagent3.xyz/skills/skill-audit/agent.json", "briefUrl": "https://openagent3.xyz/skills/skill-audit/agent.md" } }