shadcn
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
npx shadcn@latest(and alternatives likepnpm dlxorbunx) to interact with the user's project. This is the standard, documented method for managing shadcn/ui components and design systems. - [DYNAMIC_CONTEXT_INJECTION]: The
SKILL.mdfile uses the!command`` syntax to executenpx shadcn@latest info --json. This enables the agent to automatically retrieve project configuration details (framework, aliases, Tailwind version) upon loading, ensuring contextually accurate behavior without requiring user input. No user-supplied arguments are passed to this command. - [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation and usage examples from official shadcn/ui domains, specifically
ui.shadcn.comand associated GitHub repositories. These are well-known, trusted sources for the framework. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection via the processing of external documentation and component examples. This risk is effectively mitigated by the skill's extensive 'Critical Rules' (styling.md, forms.md, composition.md), which define strict constraints for the agent when generating or modifying UI code.
Audit Metadata