AGENT LAB: SKILLS

nanobanana-skill

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: 0.90). The nanobanana.py script registers a GoogleSearch tool (tools=[types.Tool(google_search=types.GoogleSearch())]) when calling client.models.generate_content, which enables the model to retrieve and consume public web search results (untrusted third‑party content) as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:38 PM