skill-menu
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
~/.codex/bin/codex-skillscommand to manage the local skill index and retrieve skill information. User-provided input is passed as an argument to this command. - [COMMAND_EXECUTION]: It accesses and reads local file definitions from directories like
~/.codex/and~/.agents/to facilitate skill discovery. - Ingestion points: Local file content from skill indexing paths.
- Boundary markers: No specific markers are used when switching to the instructions of a newly loaded skill.
- Capability inventory: File system reads and execution of the local
codex-skillsbinary. - Sanitization: The skill assumes that the contents of local skill files are safe to follow as instructions.
Audit Metadata