Deterministic reasoning runtime for AI agents. YAML rules, microsecond evaluation, zero hallucinations. Built on CLIPS.
- capability exposure inferred + 32
- recent drift inferred + 12
- tool safety inferred + 5
- 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.
graded 58s ago · see ecosystem CVEs →
- B · 29 → C · 46
- B · 32 → B · 29
No known CVEs for this server.
- medium dangerous code
dynamic exec: eval()/exec()
analyzed commit 75f44a6 · analyzer v28 · 2h ago
danger signals1
- dynamic code execution eval()/exec() KrakenNet-fathom-75f44a6/examples/05-langchain-guardrails/agent_demo.py :106
return str(eval(expression, {"__builtins__": {}}, {})) # noqa: S307
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:KrakenNet/fathom/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 KrakenNet.