nano-banana-pro

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill documentation instructs the agent to run the scripts/generate_image.py script using the uv tool.\n- [EXTERNAL_DOWNLOADS]: The Python script uses the google-genai library to connect to Google's Gemini API services for image generation tasks.\n- [DATA_EXFILTRATION]: The script transmits user prompts and, if provided, local image files to Google's API servers to fulfill the image generation or editing requests. This is expected behavior for the stated functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 10:45 AM
Security Audit — agent-trust-hub — nano-banana-pro