comfyui-llm-toolkit — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by comfy-deploy · LLM Plugin · ★ 107

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is comfyui-llm-toolkit safe to install? View the security audit →

About comfyui-llm-toolkit

ComfyUI LLM Toolkit A custom node collection for integrating various LLM (Large Language Model) providers with ComfyUI. NEW GENERAL IMAGE AND VIDEO CFGs Features True Context-to-Context node connections one-input / one-output design Generators run even if nothing is connected, and they are the only node in the workflow Streaming Output directly on the node UI Runs openai latest image model GPT-image-1 and we include various templates Text generation using various LLM providers (OpenAI and local models, etc.) Provider selection and configuration with dynamic model fetching API key management Seamless integration with ComfyUI workflows Installation @@ -33,6 +43,7 @@ The following Python packages are required: pyyaml python-dotenv requests openai Installation Clone this repository into your ComfyUI customnodes directory: bash cd

Quick Facts

Stars107
Forks19
LanguagePython
CategoryLLM Plugin
Quality Score64.0292094748617/100
Open Issues5
Last Updated2025-10-01
Created2025-04-17
Platformspython
Est. Tokens~792k

Compatible Skills

These tools work well together with comfyui-llm-toolkit for enhanced workflows:

  • llm-tools-nmap — semantic(1.00)+same_lang+similar_pop+shared_platform (55%)
  • navigator — semantic(0.25)+complementary+same_lang+similar_pop+shared_platform (54%)
  • vim-llm-agent — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (51%)

comfyui-llm-toolkit alternative? Top 5 similar tools

Looking for a comfyui-llm-toolkit alternative? If you're comparing comfyui-llm-toolkit with other llm plugin tools, these 5 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • codinit-dev by codinit-dev · ⭐ 266

    Local-First Open Source web & mobile AI app builder — install on MacOS, Windows & Linux

  • bpmn-assistant by jtlicardo · ⭐ 166

    LLM-powered assistant for creating, editing, and interpreting business process diagrams

  • lm-proxy by Nayjest · ⭐ 150

    OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch).

  • LLM_trader by qrak · ⭐ 129

    LLM-powered Crypto Trading Framework with Vision AI chart analysis, real-time Neural Engine, and a live monito

  • manim-generator by makefinks · ⭐ 117

    Automatic LLM-based video generation using the manim library. Usage of a code-writer and code-reviewer feedbac

More LLM Plugin Tools

Explore other popular llm plugin tools:

View all LLM Plugin tools →

Popular Python Agent Tools

Frequently Asked Questions

What is comfyui-llm-toolkit?

comfyui-llm-toolkit is an open-source llm plugin by comfy-deploy with 107 GitHub stars.

What programming language is comfyui-llm-toolkit written in?

comfyui-llm-toolkit is primarily written in Python.

How do I install or use comfyui-llm-toolkit?

You can find installation instructions and usage details in the comfyui-llm-toolkit GitHub repository at github.com/comfy-deploy/comfyui-llm-toolkit. The project has 107 stars and 19 forks, indicating an active community.

What are the best alternatives to comfyui-llm-toolkit?

The top alternatives to comfyui-llm-toolkit on Agent Skills Hub include codinit-dev, bpmn-assistant, lm-proxy. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse LLM Plugin tools