shadcn-components

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow can call MCP tools like mcp__shadcn__search_items_in_registries, mcp__shadcn__view_items_in_registries, and especially mcp__shadcn__get_item_examples_from_registries, which fetch and ingest outsider-authored free-form component examples/details from public/community registries into the agent’s LLM context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill instructs running "npx shadcn@latest add ..." which fetches and executes remote code from the npm registry at runtime (npx shadcn@latest), so it is a runtime external dependency that executes remote code.