OpenAI Codex CLI inside an aicodebox container. One image, five ways in: interactive shell, one-shot exec, OpenAI-compatible endpoint, MCP server, Telegram bot, and a cron scheduler. You talk to codexbox; codexbox talks to codex; codex talks to OpenAI — or your ChatGPT subscription.
- capability exposure inferred + 4
- trust mitigators mixed − 11
These factors total -7, not 0: the score is bounded to 0–100 after they are summed, so this one is floored at 0. The factors are left as they were applied rather than rewritten to make the column add up.
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 1d ago · see ecosystem CVEs →
- B · 23 → A · 0
- B · 31 → B · 23
- B · 20 → B · 31
- B · 23 → B · 20
No known CVEs for this server.
No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.
analyzed commit ede91db · analyzer v33 · 1d ago
skills & prompt files 1
[](https://mcpobservatory.com/servers/github:psyb0t/docker-codexbox/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 psyb0t.