book-cover-design

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation guidelines and resources hosted on the inference-sh GitHub repository, which is the official source for this tool.
  • [COMMAND_EXECUTION]: The instructions include usage of the belt CLI for authenticated AI image generation, refining concepts, and upscaling images. These operations are aligned with the skill's primary purpose.
  • [SAFE]: No prompt injection, data exfiltration, or obfuscation patterns were detected. The skill follows best practices by instructing users to manage credentials via belt login rather than hardcoding secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 07:48 AM