nano-banana-assets
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill communicates with
openrouter.ai, which is a well-known service for AI model aggregation. These requests are necessary for the skill's primary function of image generation. - [COMMAND_EXECUTION]: The package includes multiple scripts (
generate_asset.sh,generate_asset.py,batch_generate.py, etc.) to facilitate API interactions and local image processing. These scripts perform standard operations such as making HTTP requests and saving file output to the local disk. - [CREDENTIALS_UNSAFE]: The skill follows security best practices by instructing users to store their API key in an environment variable (
OPENROUTER_API_KEY) rather than hardcoding it in the skill's logic or metadata. - [DATA_EXFILTRATION]: While the skill sends data (prompts and reference images) to the OpenRouter API, this is the intended core functionality of the asset generator. No unauthorized data access or exfiltration patterns (such as reading system credentials or SSH keys) were identified.
Audit Metadata