Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

cursor-security-rules

bởi matank001

Cursor
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

This repository contains Cursor Security Rules designed to improve the security of both development workflows and AI agent usage within the Cursor environment. These rules aim to enforce safe coding practices, control sensitive operations, and reduce risk in AI-assisted development.

Mô tả

# 🛡️ Cursor Security Rules

This repo provides essential security rules for Cursor.

> ⚠️ **Why do you need these rules?**
> 
> By default, Cursor can generate unsafe code—such as exposing secrets or running dangerous commands. These rules act as guardrails to help you avoid risky patterns and enforce best practices automatically.

These rules aim to enforce safe coding practices, control sensitive operations, and reduce risk in AI-assisted development.

## 🚀 How to Use These Rules

✨ Simply add these rules to your `.cursor/rules` directory (or your main directory) and you'll instantly be safer.

## 📋 Example Rule Topics

- 🔒 Secure Development Principles
- 🤖 Secure MCP Usage
- 🐍 Python Security Best Practices
- 🕵️‍♂️ No Secrets in Frontend
- 🚫 No Unsafe System Commands

## 💡 Why Use Cursor Security Rules?

- ✅ Enforce safe coding practices
- 🛑 Prevent accidental exposure of secrets
- 👮‍♂️ Control sensitive operations
- 🤝 Foster a security-first development culture

## 🤝 Contribute

Are you a security researcher or developer passionate about AI safety? If you have ideas to improve these rules or want to add new ones, we encourage you to contribute! Your expertise can help make AI-assisted development safer for everyone 📝

## 👥 About Us

We are [**Matan Kotick**](https://www.linkedin.com/in/matan-kotick-664735252) and [**Amit Ziv**](https://www.linkedin.com/in/amit-ziv-49690b120), security researchers specializing in the field of AI Agents.

Contact us if you have any questions about this interesting topic!

Cài đặt

Cài kỹ năng từ https://github.com/matank001/cursor-security-rules

Kỹ năng này chưa được đăng trên registry ClawHub. Hãy dán prompt vào coding agent của bạn — Claude Code, Cursor, Codex — và nó sẽ cài kỹ năng thẳng từ kho mã nguồn.

Mở kho mã

Liên kết