gemini-3-advanced

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

• Third-party content exposure detected (high risk: 0.90). The skill enables built-in Google Search grounding and URL context fetching (see "Built-in Tools" / references/built-in-tools.md and the URL example "Summarize: https://example.com/article"), which cause the agent to fetch and read arbitrary public web pages/search results—untrusted third-party content that could carry indirect prompt injections.