Skills
Navigate
skills/wubin1836/ai-hive-agent-skills/gpt-image-2-livestream-image/Gen Agent Trust Hub

gpt-image-2-livestream-image

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses argparse to handle CLI arguments and subprocess is notably absent. It invokes webbrowser.open() during the init command to help users find their API key on the official ai-hive.iclip.cn domain, which is a standard developer experience pattern.
  • [EXTERNAL_DOWNLOADS]: The skill downloads generated image results from the AI Hive API (ai-hive.iclip.cn). These downloads are the intended primary purpose of the skill and target a consistent vendor domain.
  • [DATA_EXPOSURE]: The skill manages a local configuration file at ~/.ai-hive/config.json. It implements security best practices by explicitly setting file permissions to 0600 (read/write by owner only) using os.chmod to protect the stored API key.
  • [CREDENTIALS_SAFE]: While the skill uses an API key, it correctly avoids hardcoding secrets. It provides multiple safe methods for key management, including environment variables (AI_HIVE_API_KEY), a secure local config file, and a command-line argument. The provided config.example.json contains only placeholders.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 12:19 PM
Security Audit — agent-trust-hub — gpt-image-2-livestream-image