generation-workflow-setup

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes local utility scripts including workflow_preflight.py, workflow_catalog.py, and model_inventory.py. These scripts are used to manage workflow catalogs, materialize selections, and scan for model compatibility within the skill's relative directory structure.- [INDIRECT_PROMPT_INJECTION]: The skill processes workflow JSON files and local project configuration data, which represent a potential ingestion surface for indirect instructions.
  • Ingestion points: 00_project/workflow_preferences.json and workflow definitions stored in ../../comfyui_workflows/.
  • Boundary markers: No explicit delimiters are mentioned for the content of these JSON files.
  • Capability inventory: The skill executes local Python scripts and interacts with the ComfyUI server registry.
  • Sanitization: The instructions mandate live-validation of the selected workflow before execution and verify resource availability against the official ComfyUI registry rather than scanning the filesystem directly.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 08:40 AM