gpt-image

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches installation instructions and configuration data from the inference-sh repository on GitHub. This is a legitimate operation to set up the necessary environment for the skill's primary function.- [COMMAND_EXECUTION]: Utilizes the 'belt' CLI tool to perform image generation and editing tasks. The commands are standard for the inference.sh platform and align with the skill's description.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied prompts and external image URLs. This is an inherent feature of image generation tools. While it creates a potential surface for instructions embedded in data, the skill includes standard parameterization that does not escalate risk beyond the intended use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 10:41 AM