Self-evolving AI assistant framework. Multi-provider, multi-channel, with governance and MCP support.
- capability exposure inferred + 6
- recent drift inferred + 12
- tool safety inferred + 12
- 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 3d ago · see ecosystem CVEs →
- A · 10 → B · 22
- B · 22 → A · 10
- B · 27 → B · 22
- C · 35 → B · 27
- B · 27 → C · 35
- A · 0 → B · 27
No known CVEs for this server.
- high dangerous code
committed secret: Anthropic key, OpenAI key, private key
analyzed commit aa6e258 · analyzer v33 · 1w ago
skills & prompt files 2
- agent-rules openprx-prx-aa6e258/AGENTS.md
- agent-rules openprx-prx-aa6e258/CLAUDE.md
danger signals3
- committed secret Anthropic key openprx-prx-aa6e258/src/channels/mod.rs :10330
sk-ant…(57 chars, redacted) - committed secret OpenAI key openprx-prx-aa6e258/src/chat/sanitize.rs :168
sk-pro…(33 chars, redacted) - committed secret private key openprx-prx-aa6e258/src/gateway/compat.rs :1534
PEM private key block (redacted)
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:openprx/prx/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 openprx.