gemini-cli

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "Web Research (Google Search)" section explicitly instructs calling Gemini with "Use Google Search for current information," meaning the agent will fetch and interpret public web/search results (untrusted third-party content) and use those findings to inform its responses and actions.