codex2api-reverse-proxy
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to download the project source code and deployment configurations from a third-party GitHub repository (
https://github.com/james-6-23/codex2api.git). - [COMMAND_EXECUTION]: Provides a series of shell commands for installation and operation, including
git clone,docker compose up,npm ci, andgo run. These are standard procedures for deploying the software described in the skill. - [INDIRECT_PROMPT_INJECTION]: As a reverse proxy for LLM accounts, the service is designed to ingest and process untrusted user prompts through its API endpoints (e.g.,
/v1/chat/completions). The skill documents a "Prompt Filter" feature (Block/Warn/Modify rules) intended to mitigate risks from malicious input data.
Audit Metadata