Local-first trust layer for AI coding agents: structural prompt-injection and action guards, secret scanning, semantic memory, code review, and 17 MCP tools. No model API required.
- capability exposure inferred + 22
- tool safety inferred + 17
- 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.
grade last moved 1w ago · see ecosystem CVEs →
- B · 24 → C · 36
- C · 44 → B · 24
- D · 64 → C · 44
- C · 56 → D · 64
- D · 64 → C · 56
- C · 56 → D · 64
- C · 59 → C · 56
- A · 0 → C · 59
No known CVEs for this server.
- high dangerous code
committed secret: GitHub token · dynamic exec: eval()
- medium toxic flow (lethal trifecta)
lethal trifecta reachable across this server's tool + source surface: private-data access + untrusted-content ingestion + network exfil (a leg is proven only in the analyzed source)
analyzed commit 9ec5aad · analyzer v33 · 1d ago
danger signals4
- dynamic code execution eval() hawonb711-tech-nexus-9ec5aad/scripts/benchmark.ts :294
const result = eval(query); - dynamic code execution eval() hawonb711-tech-nexus-9ec5aad/src/review/analyzer.test.ts :231
eval(userInput); - committed secret GitHub token hawonb711-tech-nexus-9ec5aad/src/guard/guard.test.ts :70
ghp_A1…(40 chars, redacted) - committed secret GitHub token hawonb711-tech-nexus-9ec5aad/src/secrets/secrets.test.ts :62
ghp_A1…(40 chars, redacted)
[](https://mcpobservatory.com/servers/github:hawonb711-tech/nexus/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 hawonb711-tech.