code-review-and-quality
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external code and documentation, creating a surface for indirect prompt injection attacks where adversarial content in the reviewed code could attempt to override the agent's instructions. * Ingestion points: Source code, pull request descriptions, and specifications provided for review as described in SKILL.md. * Boundary markers: Not specified; the skill lacks instructions for implementing technical delimiters to isolate untrusted content from the agent's core instructions. * Capability inventory: Agents utilizing this skill typically possess broad capabilities including file system access and command execution to facilitate the review process. * Sanitization: None described for the untrusted input data.
Audit Metadata