named-persona-adversarial-review
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and defines a manual workflow for the agent to follow during code reviews. It does not include automated scripts, network operations, or sensitive file access.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external code and Pull Request data, which creates a potential surface for indirect prompt injection. However, this is a standard operational surface for a code review tool, and the instructions include explicit safeguards like the 'Integrity Check' and 'Attribution Discipline' to mitigate these risks.
- Ingestion points: Pull Request diffs and descriptions provided in the agent's context.
- Boundary markers: Not explicitly defined in the skill instructions.
- Capability inventory: Generates text-based review reports and optionally writes them to the .claude/ directory.
- Sanitization: None explicitly defined; the skill relies on technical verification and sourced principles to validate findings.
Audit Metadata