ui-system
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of natural language instructions and design constraints for UI implementation. It does not contain executable code, scripts, or hardcoded credentials.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies an attack surface for indirect prompt injection as it instructs the agent to ingest and analyze external design data such as Figma files and screenshots.
- Ingestion points: User-provided Figma files, mocks, screenshots, and live website data (SKILL.md).
- Boundary markers: Absent; the skill does not specify delimiters for separating external design data from agent instructions.
- Capability inventory: The instructions imply usage of UI tools (SVGO, visual-verify) and browser automation (Playwright) to process external assets (SKILL.md).
- Sanitization: Absent; no explicit validation or filtering of design metadata or reference content is described.
Audit Metadata