gpt-image-2-character-consistency

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The script uses standard Python libraries (argparse, requests) to build a CLI. It does not use eval(), exec(), or subprocess to run arbitrary shell commands.
  • [CREDENTIALS_UNSAFE]: The skill implements safe credential management. It guides users to store API keys in ~/.ai-hive/config.json with restricted file permissions (0600) or via environment variables. The provided config.example.json contains only placeholders.
  • [EXTERNAL_DOWNLOADS]: The script downloads generated image results from ai-hive.iclip.cn. These are the intended outputs of the skill's primary function. It also attempts to open a web browser to an official help URL during initialization.
  • [DATA_EXFILTRATION]: Network operations are restricted to the official API domain ai-hive.iclip.cn for the purpose of uploading media and submitting generation tasks. No sensitive local files (like SSH keys or AWS credentials) are accessed or transmitted.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 12:19 PM
Security Audit — agent-trust-hub — gpt-image-2-character-consistency