eval-ui-ux
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data by reading external project source code (TSX/CSS) and documentation (Markdown/JSON) to perform visual audits.
- Ingestion points: Reads files from
src/components/,src/app/,spec.md,plan.md, and content JSON files as specified in the 'Inputs Required' section. - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially embedded malicious content within the analyzed files.
- Capability inventory: The skill is limited to reading files and generating a text-based evaluation report; it does not possess file-write, network communication, or shell execution capabilities.
- Sanitization: No content sanitization or validation logic is defined to mitigate potential injection attempts from the analyzed source files.
Audit Metadata