image-2-image-edit
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the
requestsPython library to communicate with the AI Hive API. It also downloads generated image and video files from the vendor's service endpoints to the local~/Downloads/AiHivedirectory. - [COMMAND_EXECUTION]: The skill utilizes a Python script located at
scripts/imagegen.pyto process generation tasks, handle media uploads, and poll for results. This is the primary functional component of the skill. - [DATA_EXPOSURE]: The script reads and writes API credentials to a local configuration file at
~/.ai-hive/config.json. It implements security best practices by explicitly setting file permissions to0600(read/write for the owner only) to prevent unauthorized access by other local users. - [SAFE]: All network communications are directed to the vendor's official domain (
ai-hive.iclip.cn), and no evidence of prompt injection, data exfiltration, or obfuscation was found.
Audit Metadata