nano-banana

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [CREDENTIALS_SAFE]: The skill manages its API key securely by storing it in a local configuration file (~/.ai-hive/config.json) and explicitly setting restricted file permissions (0600) to ensure that only the current user can read or write the credentials.
  • [COMMAND_EXECUTION]: The script performs standard file system operations such as reading user-provided media files for upload and saving generated results to a dedicated directory in the user's Downloads folder. These actions are transparent and aligned with the tool's stated purpose.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the requests library to download generated image or video assets from URLs provided by the AI Hive API. The filenames for these downloads are generated locally to prevent path traversal issues.
  • [DATA_EXFILTRATION]: While the skill uploads media files to the AI Hive API, this is the intended core functionality of the image generation service. All communication is directed to the service's official domain (ai-hive.iclip.cn).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 12:19 PM
Security Audit — agent-trust-hub — nano-banana