Self-hosted AI knowledge base with hybrid semantic search (pgvector + FTS + RRF), MCP server, multi-provider LLM inference (Ollama, OpenAI, OpenRouter, llama.cpp), multimodal ingestion (vision, audio transcription, speaker diarization), and knowledge graph. Rust + PostgreSQL.
- capability exposure inferred + 18
- tool safety inferred + 25
- 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 →
- B · 25 → C · 35
- C · 45 → B · 25
- C · 50 → C · 45
- D · 70 → C · 50
- D · 62 → D · 70
- D · 70 → D · 62
- D · 62 → D · 70
- C · 39 → D · 62
No known CVEs for this server.
- high dangerous code
dynamic exec: eval(), new Function() · obfuscated payload: dynamic require()/import()
- high exfiltration combo manage_attachments
single tool reads + sends: fs, net, untrusted
- high toxic flow (lethal trifecta) manage_attachments
single tool reads private data, ingests untrusted content, and reaches the network: fs, net, untrusted
- medium dangerous code
env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke
- medium dangerous code
env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke
- medium dangerous code
env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke
- medium dangerous code
env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke
- medium dangerous code
env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke
- medium dangerous code
env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke
analyzed commit 306bae5 · analyzer v33 · 1d ago
skills & prompt files 4
danger signals3
- dynamic code execution eval() Fortemi-fortemi-306bae5/mcp-server/tests/annotations.test.js :46
tools = eval(`(function() { return ${bracketContent.replace(/;\s*$/, "")} })()`); - dynamic code execution eval() Fortemi-fortemi-306bae5/mcp-server/tests/schema-validation.test.js :44
tools = eval(`(function() { return ${bracketContent.replace(/;\s*$/, "")} })()`); - dynamic code execution new Function() Fortemi-fortemi-306bae5/mcp-server/validate-schemas.cjs :66
tools = new Function('path', 'return ' + arrayLiteral)(path);
[](https://mcpobservatory.com/servers/github:Fortemi/fortemi/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 Fortemi.