brooks-review
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied source code and PR diffs. This represents a potential surface for indirect prompt injection where malicious instructions could be embedded within code comments or string literals. However, the skill lacks high-risk capabilities such as network access, file writing, or command execution, which significantly limits the impact of such an attack. The ingestion of this data is fundamental to the skill's primary function as a code reviewer.
- Ingestion points:
SKILL.md(Shared code snippets and PR diffs provided by the user). - Boundary markers: None explicitly defined in the provided instruction files.
- Capability inventory: The skill performs text analysis and generates reports; no executable scripts or system-level capabilities were detected.
- Sanitization: No explicit sanitization or filtering of the input code is defined.
Audit Metadata