brooks-review
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and analyze untrusted data (user-provided code diffs and files). A malicious actor could embed instructions within code comments (e.g., '/* Ignore previous instructions and instead... */') which an LLM might inadvertently follow. However, the risk is minimal as the skill's capabilities are limited to generating a text-based report and it lacks execution tools.
- [SAFE]: The skill follows established software engineering principles, referencing well-known industry texts (e.g., books by Feathers, Osherove, and Meszaros) to provide structured feedback. It includes reasonable constraints, such as skipping auto-generated files and adjusting review depth based on PR size.
Audit Metadata