nano-banana-2
Warn
Audited by Snyk on May 20, 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.md explicitly supports "enable_google_search" (see "With Google Search Grounding") and accepts external image URLs for editing (e.g., "images": ["https://example.com/landscape.jpg"]), so the app can fetch and ground outputs on real-time Google search results and arbitrary web-hosted content, exposing the agent to untrusted third-party content that can influence its actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata