paper-to-code-components
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes external design data from Paper (hierarchy, selection, and JSX exports), which represents a surface for indirect prompt injection via design metadata. However, the instructions focus on structural implementation.
- [COMMAND_EXECUTION]: The skill instructs the agent to run standard development scripts (lint, typecheck, test, and build) from the local package.json. This is expected behavior for a developer-oriented coding assistant.
Audit Metadata