Expert-Coding-Harness: Skill for Cursor

AI Agent 安全开发最佳实践

本技能基于生产级AI Agent防护方案整理，覆盖AI系统全生命周期的安全风险防控，符合等保2.0三级要求与数据安全法规定。

When to Activate

• 开发企业级AI Agent应用
• 对接敏感内部数据的AI系统
• 实现代码执行能力的AI助手
• 合规审计要求的AI系统建设
• AI安全风险评估与加固

AI Agent 安全风险矩阵

四层安全防护架构

1. 输入层防护

Prompt注入检测

from typing import List
import re

class PromptInjectionDetector:
    def __init__(self):
        self.risk_patterns = [
            # 指令绕过模式
            r"(ignore|disregard|forget).*(previous|above|prior).*(instructions|prompt|rules)",
            r"(you are|act as|pretend to be).*(not|no longer).*(assistant|AI|bot)",
            r"(override|bypass|disable).*(security|safety|content).*(filters|policies|restrictions)",
            # 系统指令模式
            r"```system\s*",
            r"<\|system\|>",
            r"SYSTEM:",
            # 诱导输出模式
            r"(output|print|reveal|disclose).*(prompt|instructions|rules|system)",
            r"(show|tell|list).*(all|full|entire).*(prompt|context|memory)"
        ]
        self.suspicious_keywords = ["jailbreak", "DAN", "dev mode", "developer mode", "unrestricted"]
    
    def detect(self, prompt: str, threshold: float = 0.7) -> dict:
        risk_score = 0.0
        matched_patterns = []
        
        # 正则匹配检测
        for pattern in self.risk_patterns:
            if re.search(pattern, prompt, re.IGNORECASE):
                risk_score += 0.2
                matched_patterns.append(pattern)
        
        # 关键词检测
        for keyword in self.suspicious_keywords:
            if keyword.lower() in prompt.lower():
                risk_score += 0.15
        
        # 特殊字符检测
        special_char_ratio = len(re.findall(r'[^\w\s,.，。？！；：""''()（）、]', prompt)) / len(prompt) if prompt else 0
        if special_char_ratio > 0.3:
            risk_score += 0.25
        
        return {
            "is_risk": risk_score >= threshold,
            "risk_score": risk_score,
            "matched_patterns": matched_patterns
        }

# 使用示例
detector = PromptInjectionDetector()
result = detector.detect(user_input)
if result["is_risk"]:
    raise SecurityError("疑似Prompt注入攻击，请求已拦截")