gpt-image-2-multi-reference-image

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides a Python script (imagegen.py) designed to interface with the AI Hive OpenAPI. It allows the agent to initialize configurations, upload images, and trigger generation tasks via the shell.
  • [EXTERNAL_DOWNLOADS]: The script depends on the requests library, which is a standard requirement for Python-based HTTP operations. The instructions correctly guide the user to install this dependency via pip3.
  • [DATA_EXPOSURE]: The script manages sensitive API keys by storing them in a local configuration file at ~/.ai-hive/config.json. It proactively secures this data by setting file permissions to 0600 (read/write for owner only) during both initialization and subsequent reads.
  • [SAFE]: All network requests are directed to the vendor's official domain (ai-hive.iclip.cn). The cmd_init function uses the webbrowser module to open the official documentation for API key retrieval, which is a transparent and standard user-facing action.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 12:19 PM
Security Audit — agent-trust-hub — gpt-image-2-multi-reference-image