Agent-agnostic base image for putting any terminal AI coding agent (claude-code, pi, opencode...) on the network. Bolt on a 20-line adapter, get an HTTP API, OpenAI-compatible /v1/chat/completions, MCP server, Telegram bot, and cron scheduler. One container. Same surfaces. Swap the brain — you don't fork this, you FROM it.
- capability exposure inferred + 35
- 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 1d ago · see ecosystem CVEs →
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 1fdcf85 · analyzer v33 · 2d ago
danger signals1
- suspicious endpoint api.telegram.org
expected for this server's purpose
psyb0t-docker-aicodebox-1fdcf85/aicodebox/modes/cron/scheduler.py :71
url = f"https://api.telegram.org/bot{token}/sendMessage"
[](https://mcpobservatory.com/servers/github:psyb0t/docker-aicodebox/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.