a new, general and flexible KB for everything
- capability exposure inferred + 26
- recent drift inferred + 20
- tool safety inferred + 12
- 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 46s ago · see ecosystem CVEs →
- C · 40 → C · 55
No known CVEs for this server.
- high dangerous code
dynamic exec: __import__(), pickle.loads()
analyzed commit a5b46b1 · analyzer v28 · 1d ago
skills & prompt files 1
- agent-rules lucagattoni-Pinakes-a5b46b1/CLAUDE.md
danger signals3
- dynamic code execution __import__() lucagattoni-Pinakes-a5b46b1/src/pinakes/embed.py :115
return __import__(module, fromlist=["_"]) - dynamic code execution __import__() lucagattoni-Pinakes-a5b46b1/src/pinakes/extract/__init__.py :209
return __import__(module, fromlist=["_"]) - dynamic code execution pickle.loads() lucagattoni-Pinakes-a5b46b1/tests/test_cli.py :97
restored = pickle.loads(pickle.dumps(PinakesError("broke", remedy="fix it")))
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:lucagattoni/Pinakes/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 lucagattoni.