codex-exec
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute the
codexCLI tool using various flags (e.g.,--base,--uncommitted,--commit) and commands (review,exec). This allows for automated analysis of the local codebase and version control history. - [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it ingests and processes content from the local codebase, git diffs, and specific files like
PLAN.mdthrough thecodextool. - Ingestion points: Source code files and git history diffs processed via
codex reviewandcodex execinSKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions to ignore potential adversarial commands embedded within the code or files being reviewed.
- Capability inventory: The skill uses the
codexcommand-line utility for processing data. - Sanitization: There is no mention of sanitization or filtering of the content being reviewed or the output generated by the CLI tool.
Audit Metadata