nanobanana-skill

Warn

Audited by Snyk on Mar 9, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill enables the model to perform web searches and ingest arbitrary public web content via the GoogleSearch tool configured in nanobanana.py (tools=[types.Tool(google_search=types.GoogleSearch())]), so untrusted third-party pages could influence generation and subsequent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 09:04 AM