shadcn

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow mainly operates on first-party project context and CLI registry operations (e.g., npx shadcn@latest docs/view/add) rather than ingesting outsider-authored free text from a monitored queue/feed or arbitrary user text without an explicit fetch of specific registry items.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent to fetch external docs/examples and registry JSON at runtime (e.g. https://raw.githubusercontent.com/.../examples/button-example.tsx and https://api.npoint.io/abc123), which would inject remote content into the agent's context and directly influence prompts/code generation.