ah-fix-ui-bug

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow asks the agent to navigate to arbitrary page URLs ("Page URL or description (REQUIRED)") and then read and interact with those pages via chrome-devtools commands (chrome-devtools navigate_page, take_snapshot, evaluate_script, list_console_messages, etc.), which clearly ingests untrusted/public web content and uses that DOM/text data to drive diagnostics and subsequent actions.