Codex plugin for delegating reviews, rescue tasks, and media generation to Grok
- capability exposure inferred + 16
- tool safety inferred + 5
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.
grade last moved 1w ago · see ecosystem CVEs →
- A · 12 → B · 21
- A · 0 → A · 12
No known CVEs for this server.
- medium dangerous code
dynamic exec: new Function()
analyzed commit 8f76451 · analyzer v33 · 4w ago
skills & prompt files 5
- skill stdevMac-grok-in-codex-8f76451/plugins/grok/skills/grok-brand-media/SKILL.md
- skill stdevMac-grok-in-codex-8f76451/plugins/grok/skills/grok-cli-runtime/SKILL.md
- skill stdevMac-grok-in-codex-8f76451/plugins/grok/skills/grok-prompting/SKILL.md
- skill stdevMac-grok-in-codex-8f76451/plugins/grok/skills/grok-routing/SKILL.md
- skill stdevMac-grok-in-codex-8f76451/plugins/grok/skills/grok-workflows/SKILL.md
danger signals1
- dynamic code execution new Function() stdevMac-grok-in-codex-8f76451/tests/grok-parse.test.mjs :130
const embedded = new Function(`${helperSrc}; return formatStreamProgressMessage;`)();
[](https://mcpobservatory.com/servers/github:stdevMac/grok-in-codex/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 stdevMac.