gemini

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

• Third-party content exposure detected (high risk: 0.90). The skill automates gemini.google.com and explicitly instructs using the "Deep Research" tool which "returns multiple sources" and shows "Sources" below responses, meaning the agent will consume and act on synthesized content derived from open/public web sources that could contain untrusted, user-generated instructions.