Provide an open test corpus to assess and improve AI agent egress security through validated cases and automated workflows.
This grade was produced by analyzer v30 , 3 version s behind the one running now. Detectors added since have not been applied here, so it is not directly comparable with a server analyzed at the current version. A re-scan is queued.
- recent drift inferred + 20
- 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.
graded 8m ago · see ecosystem CVEs →
- B · 24 → B · 32
- A · 0 → B · 24
No known CVEs for this server.
- high dangerous code
committed secret: private key
analyzed commit 9b0874d · analyzer v30 · 2w ago
skills & prompt files 1
danger signals1
- committed secret private key bilkulsahi1235-agent-egress-bench-9b0874d/cases/mcp-input/mcp-input-ssh-key-006.json :18
PEM private key block (redacted)
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:bilkulsahi1235/agent-egress-bench/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 bilkulsahi1235.