Extract documentation for AI agents from any site with llms.txt support. Features MCP server, REST API, batch processing, and multiple export formats.
- capability exposure inferred + 24
- tool safety inferred + 5
- trust mitigators mixed − 8
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 1w ago · see ecosystem CVEs →
- A · 9 → B · 21
- B · 21 → A · 9
- B · 29 → B · 21
- C · 49 → B · 29
- C · 41 → C · 49
- B · 26 → C · 41
- C · 36 → B · 26
- C · 47 → C · 36
No known CVEs for this server.
- medium dangerous code
dynamic exec: new Function()
analyzed commit e55dd99 · analyzer v33 · 4d ago
skills & prompt files 4
- agent-rules nirholas-extract-llms-docs-e55dd99/.github/copilot-instructions.md
- agent-rules nirholas-extract-llms-docs-e55dd99/AGENTS.md
- agent-rules nirholas-extract-llms-docs-e55dd99/CLAUDE.md
- agent-rules nirholas-extract-llms-docs-e55dd99/GEMINI.md
danger signals1
- dynamic code execution new Function() nirholas-extract-llms-docs-e55dd99/public/docs/assets/javascripts/lunr/wordcut.js :5977
var render = new Function(settings.variable || 'obj', '_', source);
[](https://mcpobservatory.com/servers/github:nirholas/extract-llms-docs/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of nirholas.