apply-shadcn

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to call mcp__shadcn__get_item_examples_from_registries to pull usage examples from the (public) shadcn registries and to read/apply those examples when editing code, so untrusted third-party content can directly influence decisions and actions.