frontend-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements a structured code review process using local reference files (
references/code-quality.mdandreferences/performance.md). This architecture ensures that the logic remains consistent and verifiable. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for untrusted data as it is designed to read and analyze external source code files (
.tsx,.ts,.js). - Ingestion points: Source code files identified by the user or located in the working directory.
- Boundary markers: None explicitly defined in the prompt instructions to isolate untrusted code from instructions.
- Capability inventory: The skill only performs file reading and text generation. No file system writing, network exfiltration, or code execution capabilities were detected.
- Sanitization: No explicit sanitization or filtering of the ingested code content is mentioned.
Audit Metadata