add-ui
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill handles untrusted user input (UI artifact or redesign requests) that are interpolated into prompts to generate React and Tailwind code. This creates a surface for indirect prompt injection.
- Ingestion points: The skill's primary entry point, the
/add-uicommand, accepts a user-supplied description inSKILL.md. - Capability inventory: The agent has the capability to create and update component and route files across the project directory.
- Sanitization: The skill mitigates this risk through a mandatory 'preview and apply' protocol, ensuring generated code is inspected by the user before final integration.
- [COMMAND_EXECUTION]: The instructions guide the agent to perform command-line operations using the
shadcnCLI tool (e.g.,npx shadcn create,npx shadcn apply). These are standard operations for managing UI component libraries in modern React projects. - [EXTERNAL_DOWNLOADS]: The skill references numerous official documentation sites and community registries for UI libraries (such as shadcn/ui, TanStack, and Magic UI) to guide implementation. These references target well-known technology services and official project repositories.
Audit Metadata