code-review-quality
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a surface for indirect prompt injection because its primary function involves the ingestion and analysis of external, potentially untrusted code and pull request data.
- Ingestion points: The skill utilizes
prNumberandprFilesas primary data inputs for its review tasks. - Boundary markers: There are no specific delimiters or instructions provided to the agent to treat external code as untrusted data or to ignore embedded instructions.
- Capability inventory: The skill orchestrates multiple specialized agents with the ability to perform security and performance scanning across the codebase.
- Sanitization: No explicit validation, escaping, or filtering logic is defined for the content analyzed by the agents.
Audit Metadata