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 ryoungj · Agent Tool · ★ 223
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ToolEmu safe to install? View the security audit →
ToolEmu: Identifying the Risks of LM Agents with an LM-Emulated Sandbox [📃 Paper] [🌐 Website] [🎮 Demo] [🐦 Twitter] Recent advances in Language Model (LM) agents and tool use, exemplified by applications like ChatGPT Plugins, enable a rich set of capabilities but also amplify potential risks—such as leaking private data or causing financial losses. Identifying these risks is labor-intensive, necessitating implementing the tools, manually setting up the environment for each test scenario, and finding risky cases. As tools and agents become more complex, the high cost of testing these agents will make it increasingly difficult to find high-stakes, long-tailed risks. ToolEmu is an LM-based emulation framework that enables identifying and assessing such risks at scale, facilitating the development of safter LM agents. This repo contains the code for: testing LM agents with specific test cases in emulation evaluating LM agents with our automatic evaluators and curated benchmark [
| Stars | 223 |
| Forks | 23 |
| Language | Python |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 76.1298458243514/100 |
| Open Issues | 2 |
| Last Updated | 2024-03-22 |
| Created | 2023-09-26 |
| Platforms | python |
| Est. Tokens | ~275k |
These tools work well together with ToolEmu for enhanced workflows:
Looking for a ToolEmu alternative? If you're comparing ToolEmu with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
An open-source no-code tool for teams to collaborate on building, evaluating, and hosting applications leverag
🔍 LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). 📚 Extracts signals from promp
ChatGPT CLI is a powerful, multi-provider command-line interface for working with modern LLMs. It supports Ope
ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.
The only fully local production-grade Super SDK that provides a simple, unified, and powerful interface for ca
This is the repository for the Tool Learning survey.
Explore other popular agent tool tools:
ToolEmu is [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use. It is categorized as a Agent Tool with 223 GitHub stars.
ToolEmu is primarily written in Python. It covers topics such as agent, ai-safety, language-agent.
You can find installation instructions and usage details in the ToolEmu GitHub repository at github.com/ryoungj/ToolEmu. The project has 223 stars and 23 forks, indicating an active community.
ToolEmu is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to ToolEmu on Agent Skills Hub include anchoring-ai, langkit, chatgpt-cli. 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: