swiftui-26-api

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md "Web Content" section and the included references/webkit.md examples show WebView/WebPage loading arbitrary URLs and executing JavaScript (e.g., fetchMetadata(for url: URL) that loads a request and calls page.callJavaScript), which means the agent can fetch and programmatically interpret untrusted public web content that could carry instructions.