review
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external code, diffs, and documentation, which constitutes a surface for indirect prompt injection. However, the skill provides specific guidance to the agent to act as an adversarial reviewer, which mitigates the risk of blindly following instructions embedded in the code being reviewed.
- Ingestion points: SKILL.md directs the agent to review source code, tests, and user-provided evidence.
- Boundary markers: The skill defines a structured output format for findings and conclusions to maintain context separation.
- Capability inventory: The skill is primarily analytical; it mentions using cli-delegate for read-only subagent tasks and can transition to an implement skill for authorized fixes.
- Sanitization: The skill uses comprehensive reference documents like attack-taxonomy.md to guide the agent in objectively evaluating the safety of external content.
Audit Metadata