codex
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs users to install the
codexCLI from the official OpenAI developer website. As this is a well-known service, the reference is considered safe. - [COMMAND_EXECUTION]: The skill facilitates the execution of the
codexCLI to perform code analysis and modifications. This is the intended primary purpose of the skill. - [COMMAND_EXECUTION]: The
codex execcommand utilizes aworkspace-writesandbox mode that automatically executes shell commands and tests produced by the Codex service. The skill mitigates this risk by instructing the agent to only use this feature when explicitly requested by the user and by requiring the agent to review all resulting changes and test outputs before reporting completion.
Audit Metadata