nano-banana-2-ad-image

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions guide the user to execute a bundled Python script (imagegen.py) to interface with the AI Hive service.\n- [CREDENTIALS_UNSAFE]: The skill manages an API key for the AI Hive service. It stores the key in a local configuration file (~/.ai-hive/config.json) and includes logic to automatically enforce secure file permissions (0600), ensuring the secret is only accessible by the owner.\n- [EXTERNAL_DOWNLOADS]: The skill performs media uploads to and downloads from the service's API endpoints at ai-hive.iclip.cn.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 12:21 PM
Security Audit — agent-trust-hub — nano-banana-2-ad-image