gpt-image

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and provides installation commands for the 'belt' CLI tool via the 'belt-sh/cli' package and configuration files from the 'inference-sh' GitHub repository.
  • [COMMAND_EXECUTION]: The skill demonstrates the use of the 'belt' CLI tool to execute image generation tasks. The skill configuration restricts Bash execution to the 'belt' command only, following the principle of least privilege.
  • [PROMPT_INJECTION]: The skill defines a surface for processing user-supplied prompts and image URLs. While external data is interpolated into commands, the risk is inherent to the primary purpose of image generation and is mitigated by the scoped execution environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 03:53 PM
Security Audit — agent-trust-hub — gpt-image