test-review
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions are limited to analyzing source code and test files to identify quality issues. It does not invoke any dangerous commands, access sensitive system files, or perform network operations.
- [NO_CODE]: This skill consists entirely of markdown instructions and does not include any accompanying scripts or executable code.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided source code and test files, which constitutes a potential surface for indirect prompt injection.
- Ingestion points: Local source files, tRPC routers, React components, and test files identified via git history (SKILL.md).
- Boundary markers: None explicitly defined to delimit code from instructions.
- Capability inventory: The skill is restricted to diagnostic analysis and reporting; it lacks file-write or network-send capabilities.
- Sanitization: No specific sanitization or filtering of input code is performed.
Audit Metadata