comfyui

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: Automated alerts flagged a piped command to python3. Investigation shows the command is curl -s http://127.0.0.1:8188/queue | python3 -m json.tool, which is a safe and standard method for formatting JSON output using the Python standard library.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests ComfyUI workflow files which can execute custom Python nodes. The skill documentation provides an explicit 'Pitfalls' section warning users to inspect workflows from untrusted sources, fulfilling boundary marker and warning requirements.
  • [DYNAMIC_EXECUTION]: The underlying application (ComfyUI) utilizes dynamic execution for its node-based graph. The skill manages this surface with appropriate user warnings and path sanitization (safe_path_join) for output files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 05:58 AM