virtual-agent/ios

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow loads a campaign URL into WKWebView and injects/bridges with that page’s JavaScript, so any free-form text content authored by an outsider on that remote campaign page can be read/processed by the agent via the webview/JS message bridge (indirect prompt injection risk).