skills/tt-a1i/hermes-agent/comfyui/Gen Agent Trust Hub

comfyui

Fail

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill automates the installation of external software and packages. scripts/comfyui_setup.sh uses pipx or pip to install comfy-cli from official registries. scripts/auto_fix_deps.py facilitates the installation of ComfyUI custom nodes and models from the Comfy registry or specified URLs.
  • [COMMAND_EXECUTION]: Several scripts execute system commands to manage the ComfyUI lifecycle. scripts/hardware_check.py runs commands like nvidia-smi, rocm-smi, and PowerShell scripts to detect GPU and system resources. scripts/comfyui_setup.sh executes shell commands to install and launch the ComfyUI server.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external workflow JSON files which can contain instructions or data that influence agent behavior. As noted in the skill's own documentation, ComfyUI workflows can execute arbitrary code via custom nodes, representing a significant capability surface.
  • Ingestion points: Workflow JSON files are ingested by scripts/run_workflow.py, scripts/extract_schema.py, and scripts/check_deps.py.
  • Boundary markers: The documentation explicitly warns that 'Workflow JSON is arbitrary code' and has the same trust profile as eval.
  • Capability inventory: The skill can install packages, download models, write files, and trigger workflow execution on a server.
  • Sanitization: The skill implements safe_path_join in scripts/_common.py to prevent path-traversal attacks when downloading outputs and includes logic in scripts/_common.py to strip sensitive headers like X-API-Key during cross-host redirects.
  • [DYNAMIC_EXECUTION]: scripts/auto_fix_deps.py and scripts/run_workflow.py dynamically interact with the ComfyUI server to install nodes or execute tasks based on the contents of the processed workflow files.
  • [REMOTE_CODE_EXECUTION]: Automated scanners flagged instances of curl | python3 (e.g., in scripts/comfyui_setup.sh and SKILL.md). Analysis confirms these are used with the -m json.tool flag to pretty-print JSON data from the local server, which is a benign data-processing pattern rather than execution of remote code.
Recommendations
  • HIGH: Downloads and executes remote code from: http://127.0.0.1:$PORT/system_stats, http://127.0.0.1:8188/queue - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Aug 28, 2026, 12:48 PM
Security Audit — agent-trust-hub — comfyui