Open AI-native infrastructure for scientific knowledge — multi-persona MCP service + ingest pipeline, Apache 2.0
- capability exposureinferred+35
- trust mitigatorsmixed−11
inferredmixed
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 9m ago · see ecosystem CVEs →
- B · 27 → B · 24
No known CVEs for this server.
- highdangerous code
env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (/tmp/obs-code-zujM5f/OpenArx-AI-op
analyzed commit c862311 · analyzer v17 · 3d ago
danger signals2
- over-broad OAuth scopehttps://www.googleapis.com/auth/cloud-platformOpenArx-AI-openarx-core-c862311/packages/api/src/model-router/vertex-llm.ts:95
scope: 'https://www.googleapis.com/auth/cloud-platform https://www.googleapis.com/auth/generative-language', - over-broad OAuth scopehttps://www.googleapis.com/auth/cloud-platformOpenArx-AI-openarx-core-c862311/packages/embed-service/src/auth/service-account.ts:43
scope: 'https://www.googleapis.com/auth/cloud-platform',
[](https://mcpobservatory.com/servers/github:OpenArx-AI/openarx-core/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 OpenArx-AI.