skills/kursku/skills/shadcn/Gen Agent Trust Hub

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 like pnpm dlx or bunx) 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.md file uses the !command`` syntax to execute npx 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.com and 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
Risk Level
SAFE
Analyzed
Mar 30, 2026, 06:21 AM
Security Audit — agent-trust-hub — shadcn