chrome-ai-extension

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

• Third-party content exposure detected (high risk: 0.90). The skill's content-script examples explicitly read arbitrary page content (e.g., const selectedText = window.getSelection().toString(); and then send it for summarization/translation via summarizer.summarize(longText)), so the agent ingests untrusted third-party web content as part of its workflow, enabling indirect prompt injection.