shadcn-ui

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a utility script, scripts/verify-setup.sh, which is used to validate the project environment. This script performs diagnostic, read-only operations such as checking for the existence of configuration files (components.json, tailwind.config.js) and verifying dependencies in package.json.
  • [REMOTE_CODE_EXECUTION]: The core functionality of the skill involves directing the agent to use the npx shadcn command for project initialization and component installation. These commands interact with the well-known shadcn CLI tool via the npm registry.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of standard React components and primitives from trusted sources, including Radix UI and the official npm registry, which are essential for the shadcn/ui ecosystem.
  • [PROMPT_INJECTION]: The skill reads local project configuration files (package.json, components.json) to adapt its behavior to the project's setup. This represents a minor indirect prompt injection surface.
  • Ingestion points: Local project configuration files (package.json, components.json, tsconfig.json).
  • Boundary markers: Not present.
  • Capability inventory: The skill has access to Bash, Write, and Read tools to manage components and verify configuration.
  • Sanitization: Not explicitly implemented for configuration file ingestion.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 04:09 PM