gpt-image

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation scripts and documentation from the official inference.sh GitHub repository and domain. These are well-known resources for the associated AI inference service.\n- [SAFE]: The skill's metadata restricts tool access to the belt CLI command using the allowed-tools field, which adheres to the principle of least privilege.\n- [SAFE]: All provided command examples and parameters are consistent with the skill's primary function of image generation and editing, with no evidence of obfuscation or unauthorized data access.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 08:30 PM
Security Audit — agent-trust-hub — gpt-image