nano-banana-image-gen
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied text and images to generate content via the Gemini API. While this is a standard input surface for AI models, the skill's functionality is limited to image generation, posing minimal risk in this context.
- [SAFE]: The skill provides explicit instructions to the user on how to restrict the agent's access to the
.envfile (containing the API key) usingsettings.json, demonstrating proactive security awareness. - [SAFE]: All network operations are performed through the official Google Generative AI SDK to communicate with legitimate Google API endpoints.
- [SAFE]: No malicious command execution, data exfiltration, or obfuscation techniques were identified in the script or instructions.
Audit Metadata