ux-expert
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting and analyzing local source code files to perform UX audits, creating a potential surface for indirect prompt injection from codebase content.\n
- Ingestion points: Phase 1 instructions in
SKILL.mdexplicitly direct the agent to read components and project files (e.g.,Analytics.tsx) to understand layout and state flow.\n - Boundary markers: The instructions do not specify the use of delimiters or "ignore embedded instructions" warnings when processing the content of these files.\n
- Capability inventory: The skill identifies its output scope as ASCII wireframes, interaction specifications, and component inventory. It explicitly states it does not write production code.\n
- Sanitization: No specific sanitization or filtering logic is prescribed for handling the ingested code content.\n- [EXTERNAL_DOWNLOADS]: The
references/component-libraries.mdfile includes references and installation instructions for well-known UI libraries including shadcn/ui, Ant Design, MUI, and Recharts. These references serve as informational resources for the developer and are not executed by the agent.
Audit Metadata