XSafeClaw

by XSafeAI · Codex Skill · ★ 155

About XSafeClaw

English · 中文文档 XSafeClaw: Monitor and Secure Your Agents 🚀 🔥🔥 Now supporting OpenClaw, Hermes, and Nanobot! 🔥🔥 AI agents are not just new software. They are software that can be talked into doing dangerous things. As agents move from chatbots to active systems that browse the web, execute code, and operate inside real workflows, we have handed language models the keys to our infrastructure before figuring out how to keep them on the rails. This breaks traditional security assumptions entirely. In conventional systems, behavior is defined in code.

agent-safetyagentic-aiai-safetyllm-securityopenclawprompt-injectionred-teamingsafe-claw

Quick Facts

Stars155
Forks8
LanguagePython
CategoryCodex Skill
LicenseMIT
Quality Score63.5439690760299/100
Open Issues1
Last Updated2026-07-04
Created2026-03-10
Platformspython
Est. Tokens~17k

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is XSafeClaw?

XSafeClaw is Introducing XSafeClaw: The Open-Source Agent Safety Platform from Fudan University. It is categorized as a Codex Skill with 155 GitHub stars.

What programming language is XSafeClaw written in?

XSafeClaw is primarily written in Python. It covers topics such as agent-safety, agentic-ai, ai-safety.

How do I install or use XSafeClaw?

You can find installation instructions and usage details in the XSafeClaw GitHub repository at github.com/XSafeAI/XSafeClaw. The project has 155 stars and 8 forks, indicating an active community.

What license does XSafeClaw use?

XSafeClaw is released under the MIT license, making it free to use and modify according to the license terms.

View on GitHub → Browse Codex Skill tools