codex
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were identified in this skill.
- [COMMAND_EXECUTION]: The skill describes the usage of the Codex CLI agent harness for executing tasks. It emphasizes security best practices by detailing sandbox modes and the importance of explicit permission management.
- [EXTERNAL_DOWNLOADS]: The skill references official OpenAI documentation and verified technical resources. No unauthorized or suspicious remote code patterns were detected.
- [PROMPT_INJECTION]: The instructions focus on legitimate tool selection and task scoping, with no attempts to bypass safety filters or override agent behavior.
Audit Metadata