google-adk-python

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly shows agents using a google_search tool and says "integrate with Google Search" (e.g., LlmAgent with tools=[google_search] and an instruction "You are a helpful assistant that searches the web"), which means the agent will fetch and interpret open web search results from third-party sites as part of its workflow.