logo-design-guide

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a tutorial and workflow guide for using the belt CLI tool to interact with AI image generation models. It includes prompting best practices, design principles, and command-line examples.
  • [SAFE]: All external URLs (inference.sh, raw.githubusercontent.com/inference-sh) and referenced tools are part of the vendor's established infrastructure and represent the intended functionality of the skill.
  • [SAFE]: The skill identifies the surface for indirect prompt injection by using user input to construct image prompts, which is the primary purpose of the tool and does not present an escalation risk in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 01:07 AM