seedance-video-reference-to-video

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a standard CLI wrapper for the AI Hive OpenAPI service. No malicious behavior, obfuscation, or unauthorized data access was detected.
  • [DATA_EXPOSURE]: The skill stores an API key in ~/.ai-hive/config.json. The implementation uses os.chmod(..., 0o600) to ensure the credential file is only accessible by the current user, following standard security practices for local secret storage.
  • [COMMAND_EXECUTION]: The Python script videogen.py performs API requests using the requests library. It validates inputs and does not execute arbitrary shell commands or untrusted code strings.
  • [EXTERNAL_DOWNLOADS]: The skill downloads generated video files from the official AI Hive domain (ai-hive.iclip.cn). These downloads are the intended output of the video generation process and are initiated by the user/agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 05:16 PM
Security Audit — agent-trust-hub — seedance-video-reference-to-video