design-motion-principles
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses grep to search local source files for conditional rendering patterns. This allows the agent to find UI components that lack enter/exit transitions. This execution is limited to local searching and is safe for the intended purpose.
- [PROMPT_INJECTION]: The skill reads project files (package.json, CLAUDE.md) to weight design perspectives. This is an indirect prompt injection surface. Evidence Chain: (1) Ingestion points: package.json, CLAUDE.md, and source code; (2) Boundary markers: Absent; (3) Capability inventory: Local file read and grep; (4) Sanitization: Absent. The interaction is for analysis purposes and is not used to execute untrusted code.
Audit Metadata