nano-banana-pro
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill manages the Gemini API key through the GEMINI_API_KEY environment variable, ensuring that credentials are not hardcoded or exposed in the skill source code.
- [SAFE]: Input sanitization is performed on the user-provided prompt before it is used to construct output filenames, which mitigates risks associated with invalid characters or path manipulation in the filesystem.
- [SAFE]: Communication with external services is limited to official Google API endpoints using the verified google-genai library, which is a well-known and trusted technology service.
- [SAFE]: Filesystem access for reading reference images is an intended feature of the skill's image editing capabilities and is restricted to the paths explicitly provided by the user.
Audit Metadata