codex-review
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on executing the
codexCLI tool to perform its primary function. It runs subprocesses with various flags (--uncommitted,--base,--commit) to interact with the local git repository and source files. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted external data in the form of source code and git diffs.
- Ingestion points: The agent reads uncommitted changes, specific commits, and branch diffs via the
codex exec reviewcommand as defined inSKILL.md. - Boundary markers: No specific delimiters or instructions are provided to the agent to distinguish between its own instructions and content found within the code being reviewed.
- Capability inventory: The skill has the capability to execute commands via the
codexCLI and potentially help the user implement changes based on the review. - Sanitization: There is no evidence of sanitization or filtering of the code content before it is processed by the agent for the review task.
Audit Metadata