Demo agents showcasing CapiscIO Agent Guard and MCP Guard — trust badges, identity verification, and tool-level authorization for A2A and MCP protocols
- capability exposureinferred+28
- recent driftinferred+12
- tool safetyinferred+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.
graded 6m ago · see ecosystem CVEs →
- A · 0 → C · 52
no known CVEs for this server.
- highdangerous code
dynamic exec: eval()/exec()
analyzed commit 91de0e6 · analyzer v17 · 2h ago
skills & prompt files 1
danger signals1
- dynamic code executioneval()/exec()capiscio-a2a-demos-91de0e6/multi-agent-demo/agents/langchain-agent/main.py:159
result = eval(compile(tree, '<calc>', 'eval'), {"__builtins__": {}}, {
- recent drift+12 capability drift →
[](https://mcpobservatory.com/servers/github:capiscio/a2a-demos/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 capiscio.