nano-banana-pro
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill specifies dependencies on
google-genaiandpillow, which are well-known, standard libraries for interacting with Google APIs and processing images. - [DATA_EXFILTRATION]: The skill communicates with official Google API endpoints (
ai.google.dev) to perform image generation tasks. This is expected behavior for its stated purpose. Credentials are appropriately managed via environment variables or local configuration files rather than being hardcoded. - [COMMAND_EXECUTION]: The skill uses
uvto execute a local Python script for image processing. The operations performed—reading input images and writing the generated output to a specified path—are standard for a file-based utility tool. - [CREDENTIALS_UNSAFE]: No hardcoded API keys or secrets were found. The instructions guide users to provide the
GEMINI_API_KEYthrough secure environment variables or platform-specific configuration files.
Audit Metadata