uw-code-review
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted C# source code and documentation files for review purposes.
- Ingestion points: The skill instructs the agent to read target files for review and project documentation files (e.g.,
docs/CODING_STANDARDS.md,docs/NAMING_CONVENTIONS.md,docs/GDD.md). - Boundary markers: No specific markers or instructions to disregard embedded commands in the input data are defined.
- Capability inventory: The skill itself contains no executable scripts, network access, or file modification capabilities.
- Sanitization: Input content is not sanitized or filtered before being processed by the agent.
Audit Metadata