nanobanana

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 explicitly enables Google Search grounding (see enable_grounding=true and "Enable Google Search grounding for factual accuracy" in references/parameters.md), which means the agent fetches and interprets open web search results from the public web that can materially influence generation and tool behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 10:16 PM
Security Audit — snyk — nanobanana