Skills
Navigate
skills/halt-catch-fire/superpowers/gpt-image/Gen Agent Trust Hub

gpt-image

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a documentation and command wrapper for the GPT-Image-2 model. Its behavior is consistent with its stated purpose of image generation and editing.
  • [COMMAND_EXECUTION]: The skill utilizes the belt CLI for inference tasks. The allowed-tools configuration in the frontmatter restricts tool access to the belt command set, following the principle of least privilege.
  • [EXTERNAL_DOWNLOADS]: References and links are provided to official documentation and installation materials hosted on the inference.sh domain and its associated GitHub repositories. These are standard resources for the service provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 10:40 PM
Security Audit — agent-trust-hub — gpt-image