tdd
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides best practices for TDD and UI verification. Tool interactions with Figma and browser-based screenshot utilities are appropriate for the intended functionality and follow standard development workflows.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface through the ingestion of design data from Figma and user-provided screenshots used in the visual gate verification process. Evidence chain: 1. Ingestion points: Figma MCP and user screenshots. 2. Boundary markers: None mentioned for external visual data. 3. Capability inventory: agent-browser (open URL, screenshot) and filesystem access (create stories/tests). 4. Sanitization: No specific data validation is described for the visual design sources.
Audit Metadata