shadcn-svelte

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (references/workflows.md Phase 1/2) instructs the agent to call registry-fetch/search tools (e.g., shadcn___get_project_registries, shadcn___search_items_in_registries, shadcn___view_items_in_registries, shadcn___get_item_examples_from_registries) to load package/registry content from external registries — i.e., untrusted, user-published third‑party data that the agent will read and use to make implementation and tooling decisions, which could enable indirect prompt injection.