comfyui-workflow-builder

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill primarily provides instructions for translating natural language into ComfyUI workflow JSON formats.
  • [COMMAND_EXECUTION]: The evaluation script run-eval.sh uses system commands (python3, node, and the agent CLI) to execute test cases and validate JSON output. This is a standard development practice for skill benchmarking.
  • [EXTERNAL_DOWNLOADS]: Skill metadata lists curl and wget as requirements. These tools are commonly used in the ComfyUI ecosystem for model management and are not utilized maliciously within the skill scripts.
  • [PROMPT_INJECTION]: No instructions attempting to override safety filters or hijack agent behavior were found.
  • [DATA_EXFILTRATION]: No patterns indicative of hardcoded credentials, sensitive file access, or unauthorized network communication were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 03:50 PM