soybean-ui-component-development
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a robust implementation and audit process for UI components using standard development tools and practices.
- The instructions enforce a clear boundary between logic (headless) and presentation (UI).
- Development and validation rely on established commands (
pnpm typecheck,pnpm lint,pnpm test) and project-specific CLI utilities (pnpm sui). - External dependencies and references include well-known services and organizations, such as Playwright (Microsoft), Vue.js, and W3C (WAI-ARIA APG).
- [INDIRECT_PROMPT_INJECTION]: The skill operates on user-controlled source code and documentation within the workspace, which represents a potential injection surface.
- Ingestion points: Reads component source files (
.vue,.ts) and markdown documentation (.md) during implementation and audit phases. - Boundary markers: The skill does not explicitly define markers to separate data from instructions, but it provides strict structural templates and validation steps.
- Capability inventory: The agent can execute shell commands (
pnpm), write files across the monorepo workspaces, and run browser-based E2E tests. - Sanitization: No specific sanitization of input code is mentioned; however, the skill mandates rigorous validation through type-checking and linting after any modification.
Audit Metadata