agent-skill-trust-check
Static pre-install trust review for SKILL.md, OpenClaw, Hermes, MCP, and agent-skill marketplace packages before they request local, account, payment, or external access.
- License 许可
- MIT
- 最近更新
- 2026-11-15
- Stars
- ★ 6
- Forks
- 0
01 前言 Front Matter
- name
- agent-skill-trust-check
- spec
- usk/1.0
- tags
- [ "security", "agent-skills", "skill-review", "mcp" ]
- author
- Tate Programs
- license
- MIT
- version
- 0.1.2
- category
- security
- homepage
- https://github.com/TateLyman/agent-skill-trust-check
- changelog
- Added a marketplace-safe stdin runner that needs no filesystem or network access.
- interface
- { "type": "cli", "runtime": "node", "entry_point": "bin/agent-skill-trust-check-stdin.js", "call_pattern": "stdin_stdout" }
- description
- Static pre-install trust review for SKILL.md, OpenClaw, Hermes, MCP, and agent-skill marketplace packages before they request local, account, payment, or external access.
- permissions
- { "network": false, "env_vars": [], "filesystem": false, "subprocess": false }
- capabilities
- [ "skill_review", "agent_skill_security", "marketplace_vetting", "mcp_review" ]
- input_schema
- { "type": "object", "required": [ "text" ], "properties": { "text": { "type": "string", "description": "SKILL.md, marketplace description, or install instructions to review before installation." }, "target": { "type": "string", "description": "Optional source label for the reviewed text." } } }
- requirements
- { "node": ">=20" }
- output_schema
- { "type": "object", "properties": { "verdict": { "type": "string", "description": "Static install-readiness verdict." }, "findings": { "type": "array", "description": "Matched risky behavior signals and suggested fixes." }, "risk_score": { "type": "integer", "description": "Aggregate static risk score." }, "missing_signals": { "type": "array", "description": "Provenance or safety signals not found in the target text." } } }
- platform_compatibility
- [ "Claude Code", "Codex CLI", "Cursor", "Gemini CLI", "OpenClaw Agent" ]
02 资源文件 5
- 许可证LICENSE1.0 KB
- 参考文档package.json1.3 KB
- 参考文档README.md2.2 KB
- 参考文档skill-report.json73.7 KB
- 参考文档skill.json556 B
03 SKILL.md 正文
Agent Skill Trust Check
Use this skill before installing a third-party agent skill, SKILL.md package, MCP-linked skill, or marketplace listing.
What This Skill Does
- Reads a public or local skill description before install.
- Flags patterns that deserve review: shell execution, destructive commands, secrets, wallet/payment actions, network output, persistence, and prompt-boundary issues.
- Separates basic provenance signals from risky behavior signals.
- Produces a patch order that a maintainer can resolve before the skill is trusted.
When To Use
Use this when an agent is about to install or recommend a skill from:
- OpenClaw, Hermes, or ClawHub-style marketplaces.
- Claude Code, Codex, Cursor, Windsurf, or Gemini skill directories.
- MCP-linked skill bundles.
- GitHub repositories that include a
SKILL.md, tool manifest, or install script.
Run From The Public Repo
git clone https://github.com/TateLyman/agent-skill-trust-check.git
cd agent-skill-trust-check
npm run check
node bin/agent-skill-trust-check.js ./SKILL.md
Marketplace-safe stdin mode:
node bin/agent-skill-trust-check-stdin.js < ./SKILL.md
For JSON output:
node bin/agent-skill-trust-check.js ./SKILL.md --json
npm command:
npx --yes agent-skill-trust-check ./SKILL.md --json
Review Rules
Before installation, check:
- Does the skill run shell commands, package installers, or process-spawn APIs?
- Does it read secrets, environment variables, wallet data, credentials, cookies, or private keys?
- Does it send content to remote URLs or webhooks?
- Does it create persistent background jobs?
- Does it ask the agent to ignore or override higher-priority instructions?
- Does it document source, license, version, tests, permissions, and uninstall steps?
Boundaries
This is a static pre-install check. The marketplace-safe runner reads only stdin and returns JSON. The local CLI can also read a local path or a public GitHub/raw/Gist URL when run from the repository checkout. Neither mode executes the target skill or proves the runtime is safe.
For marketplace-grade review, use the paid Agent Skill Trust Check listing:
04 同仓库更多 Skills
serpmaven
Scrape Google search results (SERP) to JSON with SERP Maven (serpmaven) - a real Chrome browser on a residential proxy with sticky sessions. Run it as a CLI, a Python library, a local HTTP search API (`serve`), an MCP server or a Docker image; set the proxy login, workers, pages and cost tracking. Use when the user wants Google results, rank tracking, a self-hosted SERP API, or live Google search for an AI agent.
revnu-landing-page-audit
Find out why a landing page isn't turning visitors into signups, demos or sales. Audits one page against what the ad, post or search that sends people there promised, then checks the first screen, proof, call to action, friction and mobile. Returns at most 7 prioritized fixes, plus what is fine and what could not be checked; rewrites specific lines and fixes the page in the repo when asked. Never promises a conversion lift. Works without a Revnu account. Use when the user says or asks: "audit my landing page", "why isn't this page converting", "review my homepage", "my ads get clicks but no signups", "people bounce from the pricing page", "CRO review", "improve conversion rate", "is my hero section clear", "roast my landing page", "rewrite my headline", "what's wrong with this page", "landing page feedback", "make the signup page convert better". Not for SEO or AI-search audits, page speed engineering on its own, or building a new page from scratch.
revnu-growth-context
Write down once who buys, what they're stuck on, what it costs, what proof you have and what you've already tried, so every growth task starts from facts instead of a questionnaire. Creates or updates .agents/revnu-growth.md from the repo, the live site and the user, and imports an existing product-marketing.md. Use when the user says "set up our marketing context", "who is our ideal customer", "write our ICP", "describe the product for marketing", "positioning doc", "what's our brand voice", "remember this about our customers", "log what we tried", "what have we learned from marketing", "we changed pricing, update the context", "update our growth notes", "summarize the business for the agent", "import my product-marketing.md", "start a growth doc", or before a first marketing, SEO, outreach or launch task when no context file exists. Works without a Revnu account.
revnu-get-listed
Get onto the third-party pages AI answers and search cite when buyers ask for the best tool in your category: "best X" roundups, directories, review sites, GitHub awesome lists, community threads and comparison pages. Finds which ones are cited, ranks them by fit and effort, and drafts each submission, PR or pitch by the target's own rules. Use when the user says "get us listed", "which directories should we submit to", "how do we get into best-of lists", "why does ChatGPT recommend competitors and not us", "get mentioned in AI answers", "submit to awesome lists", "get on G2", "where are our competitors listed", "pitch listicle authors", "find backlink opportunities", "launch directories", "get into roundups", "Product Hunt alternatives", "where should we be listed", "get cited by Perplexity". Never submits, pays or posts without a yes. Works without a Revnu account.
revnu-ai-readiness-audit
Audit whether your website gives ChatGPT, Perplexity, Claude, Gemini and Google's AI Overviews something worth quoting, and fix the pages that don't. Use when the user says or asks "is my site ready for AI search", "audit my site for AI answers", "AEO audit", "GEO audit", "why doesn't ChatGPT quote our pricing", "make our pages citable by AI", "do I need llms.txt", "does schema help with ChatGPT", "check our structured data", "is our content visible without JavaScript", "AI SEO audit", "optimize our homepage for AI answers", "LLM SEO check", "why does AI get our product wrong", "fix our site for AI Overviews". Checks fetchability and indexability, answers in the raw HTML, entity facts, schema (including JS-injected markup), headings, dates and llms.txt, then gives at most 10 prioritised fixes and edits the repo when asked. Works without a Revnu account.
proxy-troubleshooting
Diagnose residential proxy failures, with NodeMaven's gateway as the reference - 407 with correct credentials, 406, 410, 500, a connection that hangs, ERR_TUNNEL_CONNECTION_FAILED in a browser, Playwright or Puppeteer ignoring proxy credentials, a sticky session that changes IP, geo-targeting that is silently ignored, passwords with special characters, and unexpected traffic from headless Chrome. Use when a proxy connection fails, returns the wrong location, or costs more traffic than expected.