shadcn
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill employs dynamic context injection to run 'npx shadcn@latest info --json' at load time, ensuring the agent has up-to-date project context. This is a standard and safe operation for this toolset.
- [EXTERNAL_DOWNLOADS]: The skill uses the 'shadcn' CLI and fetches documentation/examples from 'ui.shadcn.com' and official GitHub repositories. These are well-known technology services and are documented neutrally.
- [DATA_EXFILTRATION]: Documentation regarding MCP server configuration mentions environment variable resolution in registry headers. While potentially sensitive, this is a standard feature for private registry authentication.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection via external registry content and documentation, but includes mitigation strategies such as explicit registry selection and user confirmation prompts.
Audit Metadata