Open-source AI Agent Security Scanner — OWASP ZAP for AI Agents. Scan MCP configs, monitor agent behavior, detect permission drift, simulate policy impact.
- capability exposure inferred + 16
- 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 2m ago · see ecosystem CVEs →
- A · 13 → B · 30
No known CVEs for this server.
- medium dangerous code
dynamic exec: eval()/exec()
analyzed commit 36df45c · analyzer v28 · 1d ago
danger signals1
- dynamic code execution eval()/exec() arshan846-pluto-aguard-36df45c/examples/demo-agent-project/agent.py :24
result = eval(response.choices[0].message.content)
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:arshan846/pluto-aguard/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 arshan846.