google-adk

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly includes and instructs use of built-in web search tools (e.g., google_search listed in references/tools-and-sessions.md and guidance in SKILL.md/references/agent-design.md to "Use search_web(query)" and to run web_searcher/news_searcher/arxiv_searcher), so agents will fetch and read public/untrusted web and news content that can materially influence tool use and subsequent actions.