Claude Code and Claude Desktop MCP plugin that lets Claude supervise OpenAI Codex through gated implementation slices.
This grade was produced by analyzer v27 , 6 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.
- capability exposure inferred + 16
- tool safety inferred + 5
- 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 3d ago · see ecosystem CVEs →
- B · 30 → B · 18
- C · 38 → B · 30
- C · 44 → C · 38
- C · 51 → C · 44
- C · 37 → C · 51
No known CVEs for this server.
- medium dangerous code
dynamic exec: new Function()
analyzed commit 9d7bb09 · analyzer v27 · 7w ago
skills & prompt files 3
danger signals1
- dynamic code execution new Function() tomtastisch-codex-orchestrator-9d7bb09/bundle/server.mjs :2953
const makeValidate = new Function(`${names_1.default.self}`, `${names_1.default.scope}`, sourceCode);
[](https://mcpobservatory.com/servers/github:tomtastisch/codex-orchestrator/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 tomtastisch.