gpt-image
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. All identified operations align with the skill's stated purpose of image generation.
- [EXTERNAL_DOWNLOADS]: The skill references documentation and installation scripts from the official 'inference-sh' GitHub repository. These are verified vendor resources.
- [COMMAND_EXECUTION]: Shell access is strictly limited to the 'belt' command via the Bash tool. This restriction prevents the agent from executing arbitrary system commands beyond the specific functionality required for the skill.
Audit Metadata