self-review
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions designed to guide the agent through a code quality review process.
- [DATA_EXPOSURE]: The skill instructs the agent to read changed files in the project. This is standard behavior for a development-oriented skill and does not involve exfiltration to external domains.
- [COMMAND_EXECUTION]: The process section includes a step to fix identified issues, which utilizes the agent's existing file-writing capabilities to perform the intended self-correction task.
- [PROMPT_INJECTION]: The inclusion of the
$ARGUMENTSplaceholder at the end of the file is a standard mechanism for passing parameters and does not contain any malicious override instructions.
Audit Metadata