nanobanana-skill

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses the official google-genai library to interact with Google's services. All external dependencies (Pillow, python-dotenv, httpx) are standard, well-maintained packages from the official PyPI registry.
  • [SAFE]: Sensitive information (GEMINI_API_KEY) is handled via environment variables or a local hidden file (~/.nanobanana.env), which is a standard security practice to avoid hardcoding credentials.
  • [SAFE]: Command execution is limited to running the included Python script. The script uses argparse for safe argument parsing and does not employ dangerous functions like eval() or os.system() on raw user input.
  • [SAFE]: File system operations are restricted to reading input images provided by the user and saving the generated output to a specified or auto-generated path.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:58 AM