gpt-image
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references documentation and installation guidelines hosted on the official GitHub repository for inference-sh, which is the service provider for the model being accessed.
- [COMMAND_EXECUTION]: Utilizes the
beltCLI tool to execute model inference. The scope of execution is restricted in the frontmatter to thebeltcommand, adhering to the principle of least privilege. - [PROMPT_INJECTION]: The skill processes user-supplied prompts for image generation. This follows the intended use case for generative AI tasks, though it constitutes an inherent surface for indirect prompt injection as defined by the processing of untrusted data.
Audit Metadata