google-flow-prompting

Warn

Audited by Snyk on Mar 10, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly states in "Gap 1 — Search Grounding" that Nano Banana 2 can query Google Search / live web references (e.g., "Based on current Google Search data for [subject], render..."), which demonstrates the agent fetches and uses open/public third‑party content that can materially influence generation behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 10:12 PM