nanobanana

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill's GenerateContentConfig explicitly includes tools=[types.Tool(google_search=types.GoogleSearch())], which allows the model to perform web searches and ingest public third-party search results (untrusted user-generated/open web content) into its generation workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:22 PM