skills/openai/plugins/shadcn/Gen Agent Trust Hub

shadcn

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • Dynamic Context Injection: The skill employs the !command syntax to execute npx shadcn@latest info upon loading. This automatically populates the agent's context with project-specific details such as import aliases, Tailwind configuration, and installed components.
  • Command Execution via CLI: Instructions guide the agent to perform project tasks using the shadcn CLI through package runners like npx, pnpm dlx, or bunx. This is the standard operational model for adding and managing UI components.
  • External Documentation Retrieval: The workflow involves generating documentation and example URLs via the CLI, which the agent then fetches. This ensures the assistant uses current API references and best practices directly from official registries and repositories.
  • Indirect Prompt Injection Surface: The skill is designed to ingest and process data from external documentation URLs and registry files. While this represents a potential surface for indirect prompt injection if those sources were compromised, the instructions prioritize official vendor-controlled domains and repositories.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 03:11 PM