Agent-native geometry kernel: a Rust B-Rep engine where every operation returns a validity certificate — nine structural invariants, computed under the write lock, failing closed. Outside its verified envelope it refuses with a typed error rather than approximating. The kernel cannot lie.
- capability exposure inferred + 35
- 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 7m ago · see ecosystem CVEs →
- C · 59 → D · 67
- C · 35 → C · 59
- B · 22 → C · 35
No known CVEs for this server.
- high dangerous code
committed secret: Anthropic key · obfuscated payload: dynamic require()/import()
analyzed commit f71773b · analyzer v32 · 1h ago
skills & prompt files 2
- agent-rules varun29ankuS-Roshera-CAD-f71773b/CLAUDE.md
- agent-rules varun29ankuS-Roshera-CAD-f71773b/roshera-backend/CLAUDE.md
danger signals1
- committed secret Anthropic key varun29ankuS-Roshera-CAD-f71773b/roshera-backend/api-server/src/ai_provider_config.rs :1803
sk-ant…(36 chars, redacted)
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:varun29ankuS/Roshera-CAD/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 varun29ankuS.