Open-source native operator for the governed AMOS company brain — model-independent, locally capable, and human-governed.
- capability exposure inferred + 22
- recent drift inferred + 20
- tool safety inferred + 14
- 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 10m ago · see ecosystem CVEs →
- C · 51 → C · 53
- C · 43 → C · 51
- C · 35 → C · 43
- C · 38 → C · 35
- C · 51 → C · 38
No known CVEs for this server.
- high dangerous code
dynamic exec: vm exec
- low exfiltration combo
sensitive read and network capabilities split across this server's tools
analyzed commit 386d340 · analyzer v32 · 2h ago
danger signals4
- dynamic code execution vm exec amos-labs-amos-agent-386d340/scripts/benchmarkLocalModels.js :218
vm.runInNewContext( - suspicious endpoint 93.184.216.34 amos-labs-amos-agent-386d340/test/browser.test.js :435
url: "https://93.184.216.34/callback?access_token=secret", - suspicious endpoint 169.254.169.254 (cloud metadata) amos-labs-amos-agent-386d340/test/documentArtifacts.test.js :48
sources: [{ label: "Metadata", url: "http://169.254.169.254/latest/meta-data" }] - suspicious endpoint 93.184.216.34 amos-labs-amos-agent-386d340/test/web.test.js :20
() => fetchPublicUrl("http://93.184.216.34/start", { fetchImpl: async () => { calls += 1; return response; } }),
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:amos-labs/amos-agent/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 amos-labs.