nano-banana-pro
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses official and well-known libraries (
google-genaiandpillow) to interact with Google's Gemini API for image generation. All network communication is directed to Google's infrastructure. - [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes user-provided prompts and input images to generate content.
- Ingestion points: The
scripts/generate_image.pyscript accepts external data via the--promptand--input-imagearguments. - Boundary markers: No explicit boundary markers or 'ignore' instructions are used to wrap the input prompt before it is sent to the model.
- Capability inventory: The script has file-write capabilities (saving generated images to disk) and network access to the Gemini API.
- Sanitization: There is no manual sanitization of the input strings; however, the content is processed by the Gemini model which typically applies its own safety and instruction-following guardrails.
Audit Metadata