The Agent Skills Directory

[SAFE]: The skill is designed for frontend development assistance. It provides comprehensive documentation, implementation examples, and configuration guidance for shadcn/ui.
[COMMAND_EXECUTION]: The skill uses standard CLI commands such as npx shadcn@latest init and npx shadcn@latest add. These are the official, well-known methods for managing shadcn/ui components.
[EXTERNAL_DOWNLOADS]: The skill references standard npm packages (e.g., react-hook-form, zod, @tanstack/react-table) and official shadcn/ui registries. These are trusted, well-known technology sources and do not represent a security risk in this context.
[REMOTE_CODE_EXECUTION]: There is no evidence of untrusted remote code execution. All suggested commands target official repositories or standard package managers.
[PROMPT_INJECTION]: The core instructions in SKILL.md are focused on technical guidance and do not contain any attempt to override safety filters or bypass agent constraints.
[DATA_EXFILTRATION]: No sensitive file access or unauthorized network operations were detected. The web_fetch tool is enabled but used for legitimate documentation and component discovery.
[DYNAMIC_EXECUTION]: No usage of eval(), exec(), or runtime compilation of untrusted code was found.

shadcn-ui