Nano Banana

Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K...

This skill appears to implement Gemini-based image generation and editing and does not contain obvious exfiltration. However: - The script requires a GEMINI_API_KEY (or --api-key) but the registry metadata does not declare that requirement — verify you are comfortable supplying an API key and that the key has appropriate (limited) permissions and quota. - There is no install spec: you must ensure Python >=3.10 and install google-genai and pillow before running. Consider running it in an isolated environment (virtualenv/container) first. - Metadata mismatch: ownerId in _meta.json differs from registry ownerId and the source/homepage are unknown. Prefer skills with a verifiable source or published homepage. - Review the code yourself (or have someone you trust review it) before providing credentials. If you proceed, keep the API key scoped to a dedicated account, avoid reusing high-privilege keys, and run the script from a sandbox until you confirm behavior. If you want, I can list the exact commands to create a virtualenv and install the dependencies, or help you verify the GEMINI API key scope and revoke it later.

Type: OpenClaw Skill Name: nano-banana-pro1 Version: 1.0.0 The skill is a legitimate image generation and editing tool designed to interface with Google's GenAI API. The Python script (generate_image.py) uses standard libraries like google-genai and Pillow to process images and save them to the local filesystem, while the SKILL.md provides clear, helpful instructions for the AI agent, including safe filename conventions and resolution mapping. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.