gemini-search
Warn
Audited by Snyk on Nov 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required search route sends queries to Google Search through Gemini, and the model ingests arbitrary public web page text from results it selects, which the rubric treats as low-exposure outsider content the agent must actively fetch, with
readalso ingesting user-supplied outsider URLs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata