ui-critique

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

• Third-party content exposure detected (high risk: 0.70). The skill’s workflow includes analyzing a UI via critique_ui(screenshot, url) and checks like check_mobile_view(url) / check_performance(url) / check_aria_and_semantics(url), which at runtime implies fetching or extracting page content from an arbitrary url (public web content) and feeding it into the LLM context.