gpt-image
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references installation instructions and resources from the official inference-sh GitHub repository and the inference.sh domain.
- [COMMAND_EXECUTION]: The skill is configured to use the belt CLI tool specifically for running image generation models.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data through text prompts and image URLs. Ingestion points: 'prompt', 'images', and 'mask' parameters in SKILL.md. Boundary markers: None. Capability inventory: Execution of 'belt' CLI commands as defined in allowed-tools. Sanitization: None present. The risk is considered standard for the skill's primary function of image generation.
Audit Metadata