gemini-interactions-api

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly includes Google Search and URL context tools and the Deep Research agent in SKILL.md (see "Tool orchestration" and the Data Model entries like google_search_call / url_context_call and the background Deep Research examples), which indicates the agent will fetch and interpret public web/third-party content that can influence its actions.