frontend-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external frontend code files provided by the user, which constitutes a surface for indirect prompt injection attacks.\n
- Ingestion points: The agent reads and analyzes user-provided .tsx, .ts, and .js files from the
src/frontend/directory.\n - Boundary markers: The skill instructions lack explicit delimiters or instructions to ignore embedded commands within the code or comments of the files being reviewed.\n
- Capability inventory: The skill allows the agent to review code and propose actionable fixes, with a prompt to apply these changes to the files, indicating file-writing capabilities.\n
- Sanitization: There is no evidence of sanitization or filtering of the content within the reviewed code before it is ingested into the agent's context.
Audit Metadata