nano-banana-pro

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as a standard API wrapper for Google's Gemini image generation services without any malicious behavior.
  • [EXTERNAL_DOWNLOADS]: All dependencies (google-genai, pillow) are well-known, trusted, and managed through the standard uv package manager.
  • [CREDENTIALS_UNSAFE]: The skill follows security best practices by retrieving the GEMINI_API_KEY from environment variables or command-line arguments rather than using hardcoded secrets.
  • [DATA_EXFILTRATION]: Network activity is confined to the official Google API endpoint for its intended purpose. No unauthorized data transmission or sensitive file access was detected.
  • [COMMAND_EXECUTION]: The skill uses uv run for script execution, which is a safe and standard method for running Python scripts with managed dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 01:53 AM