shadcn-ui
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the official
shadcnCLI utility (npx shadcn@latest) for project initialization and component management. This is the standard, documented method for managing shadcn/ui components. - [INDIRECT_PROMPT_INJECTION]: The skill utilizes MCP tools to fetch data from component registries. While this represents a data ingestion surface, the interaction is scoped to structured component definitions and metadata required for frontend development.
- Ingestion points: MCP tools like
list_componentsandget_componentinSKILL.md. - Boundary markers: Not explicitly defined in the instruction text.
- Capability inventory: The skill has access to
Bash,Write, andReadtools to facilitate file generation and environment checks. - Sanitization: Standard tool output processing is expected from the platform environment.
- [REMOTE_CODE_EXECUTION]: The skill references a set of well-known, high-reputation Node.js packages (e.g., Radix UI primitives, TanStack Table, Zod) used as peer dependencies for the UI components. No suspicious or unversioned remote scripts are executed.
Audit Metadata