Persistent, semantically-searchable memory and a symbol-level code graph for AI coding agents. One static Rust binary — SQLite or PostgreSQL, MCP-compatible.
- capability exposure inferred + 14
- recent drift inferred + 12
- tool safety inferred + 19
- trust mitigators mixed − 3
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 4h ago · see ecosystem CVEs →
- C · 50 → C · 42
- C · 51 → C · 50
- C · 43 → C · 51
No known CVEs for this server.
- high dangerous code
committed secret: GitHub fine-grained PAT
- medium toxic flow (lethal trifecta)
lethal trifecta reachable across this server's tools: private-data access + untrusted-content ingestion + network exfil
- low exfiltration combo
sensitive read and network capabilities split across this server's tools
analyzed commit 6822487 · analyzer v33 · 6d ago
skills & prompt files 1
- agent-rules crlome-runar-forge-6822487/CLAUDE.md
danger signals1
- committed secret GitHub fine-grained PAT crlome-runar-forge-6822487/crates/muninn/src/redact.rs :428
github…(44 chars, redacted)
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:crlome/runar-forge/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 crlome.