gemini-search-mcp-web-search
Warn
Audited by Snyk on Jun 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). The required runtime workflow for
web_search(query)/ask(prompt)uses a real browser (CDP) to fetch and parse Google search/AI Mode results, so outsider-authored free text from public web pages (and Google-generated snippets) is ingested into the agent’s LLM context as synthesized grounded content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata