nano-banana-character-consistency

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses the well-known requests Python library to communicate with the official AI Hive API endpoint at https://ai-hive.iclip.cn/api. These network operations are essential for the skill's primary function of image generation and media management.
  • [SAFE]: The skill implements secure credential management by storing the user's API key in a local configuration file (~/.ai-hive/config.json) and explicitly setting restrictive file permissions (mode 0600) to prevent other users on the system from reading the secret.
  • [SAFE]: The init command provides a user-friendly way to configure the API key, including opening the official documentation in a web browser, which helps prevent users from inadvertently exposing their keys through insecure channels.
  • [SAFE]: File system operations are limited to reading user-provided image files for upload and writing generated results to the user's Downloads directory, which is consistent with the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 12:19 PM
Security Audit — agent-trust-hub — nano-banana-character-consistency