frontend-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external frontend source code files, which serves as an ingestion point for untrusted data that could contain malicious instructions designed to influence the agent.
- Ingestion points: Files with extensions .tsx, .ts, and .js provided by the user for review.
- Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded within the code comments or strings of the files being analyzed.
- Capability inventory: The skill reads file contents and provides code modification suggestions, which may be applied to the filesystem if the user agrees.
- Sanitization: No specific sanitization or validation of the input code content is performed before processing.
Audit Metadata