shadcn-ui

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow is primarily local CLI/MCP calls to fetch shadcn/ui component source code (e.g., via get_component/get_block) and install it; this ingested text is from the shadcn/ui project (an external publisher), which is outsider-authored free text entering the agent context.