frontend-designer

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

• Third-party content exposure detected (high risk: 0.80). The skill includes a DataFetcher render-props example in references/component_library.md that performs fetch(url) on a supplied URL and passes the returned data into the component render flow, which clearly ingests arbitrary/untrusted third‑party content from user-provided URLs.