review-ux-ui
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and metadata do not contain any malicious patterns or deceptive content. All procedures described are standard for UX/UI auditing.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface as it is designed to ingest and process external content from URLs and source code. Evidence Chain: 1. Ingestion points: External application content and source code are accessed via WebFetch and Read tools as defined in the procedure; 2. Boundary markers: No specific delimiters or 'ignore' instructions are provided for processed content; 3. Capability inventory: The skill is limited to Read, Grep, Glob, and WebFetch tools, lacking any dangerous capabilities such as shell execution or file writing; 4. Sanitization: No explicit sanitization of input data is described. This is a low-risk vulnerability surface that is inherent to the primary purpose of a review skill.
- [COMMAND_EXECUTION]: No dangerous command execution or privilege escalation patterns were found. The tool permissions are appropriately scoped to read-only operations necessary for interface analysis.
Audit Metadata