code-review
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill instructs the agent to run standard development commands (e.g.,
pnpm test,npm run build,cargo test) to verify code quality. These are localized to the development environment and are appropriate for the skill's purpose. - [PROMPT_INJECTION] (SAFE): No instructions were found that attempt to bypass safety filters, reveal system prompts, or override agent constraints. The instructions are focused solely on professional code review protocols.
- [DATA_EXPOSURE] (SAFE): The skill does not access sensitive file paths or hardcode any credentials.
- [INDIRECT_PROMPT_INJECTION] (SAFE): Although the skill is designed to process external feedback (untrusted data), it includes specific defensive instructions to 'Verify technically before implementing' and 'Push back with reasoning if wrong,' which serves as a safeguard against malicious or incorrect suggestions.
Audit Metadata