shadcn-management

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly calls registry-fetching routines (e.g., shadcn___search_items_in_registries, shadcn___view_items_in_registries, shadcn___get_item_examples_from_registries) to retrieve public component implementations and example code from registries, which are third-party sources the agent is expected to read and interpret as part of its workflow.