AI Agent Permission & Access Auditor — surfaces the lethal trifecta of credentials + injection + reach
- capability exposure inferred + 22
- recent drift inferred + 12
- tool safety inferred + 12
inferred
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 →
- C · 54 → C · 46
- C · 46 → C · 54
- C · 54 → C · 46
- C · 39 → C · 54
- C · 47 → C · 39
- C · 54 → C · 47
- C · 46 → C · 54
- A · 0 → C · 46
No known CVEs for this server.
- high dangerous code
committed secret: OpenAI key · dynamic exec: eval()/exec()
analyzed commit 2e75bcc · analyzer v33 · 1w ago
danger signals2
- dynamic code execution eval()/exec() cognis-digital-aegis-2e75bcc/demos/coding-assistant/agent.py :42
return eval(expr) - committed secret OpenAI key cognis-digital-aegis-2e75bcc/demos/04-supply-chain-mcp/agent.py :5
sk-aDD…(51 chars, redacted)
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:cognis-digital/aegis/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 cognis-digital.