ai-code-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is intended to process and review external, AI-generated code, which constitutes a surface for indirect prompt injection if the ingested code contains hidden or adversarial instructions.
- Ingestion points: The skill acts upon AI-generated code provided in the user context (SKILL.md).
- Boundary markers: The skill provides a structured review framework but does not define explicit delimiters for the code under review.
- Capability inventory: The skill lists standard CLI tools (tsc, eslint, audit-ci) for the agent or user to execute for validation.
- Sanitization: No automated sanitization is performed by the skill itself, as it is a set of guidelines and manual checkpoints.
Audit Metadata