ai-image-generation

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill operates as a standard integration for an image generation service. All provided commands and links are consistent with the stated goal of interacting with the inference.sh platform.
  • [COMMAND_EXECUTION]: The skill provides examples of executing the belt CLI tool to run inference jobs. These commands use structured JSON inputs for prompts and parameters, which is a standard pattern for AI service interaction.
  • [EXTERNAL_DOWNLOADS]: The documentation references an external installation guide and markdown file hosted on GitHub (inference-sh/skills). These references are used for documentation and setup instructions and do not involve direct piped execution of remote scripts.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text through prompts passed to image generation models. This is the primary function of the skill and the use of JSON-formatted inputs helps maintain clear boundaries between the command structure and the user data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 11:26 AM
Security Audit — agent-trust-hub — ai-image-generation