The Agience developer SDK for Python. An environment adapter.
- 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.
grade last moved 1d ago · see ecosystem CVEs →
- A · 5 → A · 2
No known CVEs for this server.
- medium dangerous code
dynamic exec: eval()/exec()
analyzed commit 101f1b3 · analyzer v33 · 5d ago
danger signals1
- dynamic code execution eval()/exec() Agience-agience-prism-py-101f1b3/src/prism/runner.py :561
exec(code, module.__dict__)
[](https://mcpobservatory.com/servers/github:Agience/agience-prism-py/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 Agience.