prototype
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a structured methodology for UX/UI prototyping, transitioning from content-first ideas to code artifacts. It references local template and configuration files stored in the shared vendor directory (
.claude/skills/_ux-ui-shared/).- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user-provided ideas as the basis for design artifacts and user journey maps. While this represents a potential surface for indirect prompt injection, the risk is minimal due to the narrow scope of the design task. - Ingestion points: User-provided ideas for prototyping and identifying needs (Step 1 and 2).
- Boundary markers: None present to delimit user input from the agent's instructions.
- Capability inventory: Read operations for local shared assets such as tokens, components, and accessibility guidelines.
- Sanitization: No input sanitization is specified for the user's idea before it is used to generate journey maps or wireframes.
Audit Metadata