gemini-image-generator

Warn

Audited by Snyk on Mar 6, 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 automates a browser to navigate to gemini.google.com, upload reference images, and extract Gemini's AI-generated YAML analysis from the public web UI which is then read and used to build optimized meta-prompts and drive subsequent image-generation actions, exposing the agent to untrusted third-party content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 06:53 AM