minimax-h3-image-to-video

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill communicates with the official API endpoint at ai-hive.iclip.cn for model lookups, media uploads, and video generation, which is consistent with its stated purpose.
  • [SAFE]: Credential management is handled by storing API keys in a local configuration file at ~/.ai-hive/config.json with restrictive file permissions (0600) automatically applied to prevent unauthorized local access.
  • [SAFE]: The skill uses the well-known requests Python library for all network operations and does not employ any obfuscation or remote code execution techniques.
  • [EXTERNAL_DOWNLOADS]: Downloads generated video results from the API to a local directory defined by the user (defaulting to ~/Downloads/AiHive).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 12:20 PM
Security Audit — agent-trust-hub — minimax-h3-image-to-video