ai-image-generation

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill provides legitimate instructions for generating images using AI models via the belt command-line interface. All documented tools and external links point to the official inference.sh platform and its associated repositories.- [EXTERNAL_DOWNLOADS]: References installation guidelines from the official inference.sh GitHub repository.- [COMMAND_EXECUTION]: Instructs the agent to use the belt CLI tool via Bash to perform tasks such as authentication, listing applications, and running image generation models.- [PROMPT_INJECTION]: The skill provides an interface for processing user-defined prompts and external image URLs through structured JSON inputs. Boundary markers are enforced by the JSON schema used in the command-line arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 08:29 PM
Security Audit — agent-trust-hub — ai-image-generation