add-ui

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly directs the agent (in reference/component-library-integration.md and related SKILL.md guidance) to "check official upstream documentation" and "do a focused web search" (with links to ui.shadcn.com, tailwindcss.com, etc.), meaning the agent will fetch and read public third‑party web content that can materially influence tooling and implementation decisions.