AgentShield

针对 LLM 的提示词注入检测器，结合启发式规则、向量相似度和语言模型多重防御策略，有效识别和阻止恶意提示注入攻击。

Enterprise AI Platform with guardrails, MCP registry, gateway and orchestrator — comprehensive AI agent governance and management.

The Python Risk Identification Tool for generative AI — an open-source framework by Microsoft for proactively identifying risks in generative AI systems through red teaming and automated probing.

LLM 交互安全工具包，提供提示词注入检测、敏感信息脱敏、内容安全审计等防护能力，保障生产环境 LLM 调用的安全性。