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 Chenyu-Wang567 · LLM Plugin · ★ 143
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is MLLM-Tool safe to install? View the security audit →
MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learning Chenyu Wang, Weixin Luo, Qianyu Chen, Haonan Mai, Jindi Guo, Sixun Dong, Xiaohua (Michael) Xuan, Zhengxin Li, Lin Ma, Shenghua Gao. ShanghaiTech University && Meituan && UniDT This repository hosts the code, data and model weight of MLLM-Tool, the first tool agent MLLM that has the ability to perceive visual- and auditory- input information and recommend appropriate tools for multi-modal instructions. 🎉 News [x] [2024.02.02] 📢📢 We change the permissions for data and checkpoints, no longer need to apply to download them. [x] [2024.01.16] 🚀🚀 Release the code of MLLM-Tool. [x] [2024.01.16] 🔨🧩 Release the ToolMMBench dataset. [x] [2024.01.16] 📢📢 Release the checkpoint of MLLM-Tool in Vicuna-7B, Vicuna-13B, Llama-7B, Llama-13B, Llama2-7B, Llama2-13B, Llama2Chat-7B, Llama2Chat-13B. 👉 TODO [ ] Collect more data and release the v2 dataset. [ ] Update MLLM-Tool in more types & sizes of LLMs. [ ] Empower MLLM-Tool with retrieving open-set tools. [ ] Release Demo and Inter
| Stars | 143 |
| Forks | 5 |
| Language | Python |
| Category | LLM Plugin |
| License | MIT |
| Quality Score | 70.5185970262236/100 |
| Open Issues | 5 |
| Last Updated | 2025-10-10 |
| Created | 2024-01-08 |
| Platforms | python |
| Est. Tokens | ~193k |
These tools work well together with MLLM-Tool for enhanced workflows:
Looking for a MLLM-Tool alternative? If you're comparing MLLM-Tool with other llm plugin tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Official Implementation of Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Opt
A simple GPT-based evaluation tool for multi-aspect, interpretable assessment of LLMs.
🎨 Vibe Design System - Official monday.com UI resources for application development in React.js
Shell and coding agent on mcp clients
ChatGPT Copilot Extension for Visual Studio Code
[CVPR 2025 🔥]A Large Multimodal Model for Pixel-Level Visual Grounding in Videos
Explore other popular llm plugin tools:
MLLM-Tool is MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learning. It is categorized as a LLM Plugin with 143 GitHub stars.
MLLM-Tool is primarily written in Python. It covers topics such as gpt4, llm, lmm.
You can find installation instructions and usage details in the MLLM-Tool GitHub repository at github.com/Chenyu-Wang567/MLLM-Tool. The project has 143 stars and 5 forks, indicating an active community.
MLLM-Tool is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to MLLM-Tool on Agent Skills Hub include DyLAN, just-eval, vibe. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: