ux-review
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional text for the AI agent to act as a UX reviewer. No malicious code, credential harvesting, or unauthorized data access patterns were detected.- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing external content by instructing the agent to read real code or web pages for review.
- Ingestion points: Source code and web pages processed during the UI verification phase.
- Boundary markers: No specific delimiters or safety instructions are defined to separate user-provided data from agent instructions.
- Capability inventory: The skill uses standard file reading and the
verify-uitool. No capabilities for network exfiltration or destructive file system operations are requested. - Sanitization: The instructions do not specify any validation or sanitization steps for the ingested external content.
Audit Metadata