leeroy-jankins/OWASP-Agentic-AI-Threats

OWASP代理AI威胁与缓解问答数据集是一个基于OWASP代理AI-威胁与缓解报告的合成指令式问答数据集。该数据集旨在支持与代理AI安全、大语言模型代理、多代理系统、威胁建模、自主工具使用、代理内存、身份风险、人在回路控制以及缓解策略相关的训练、微调、检索评估和领域特定问答用例。源文档重点关注基于大语言模型的代理，因为这类代理扩展了代理AI应用的规模、自主性、能力和风险。

The OWASP Agentic AI Threats and Mitigations Question Answering Dataset is a synthetic instruction-style question-answering dataset derived from the OWASP Agentic AI - Threats and Mitigations report. The dataset is designed to support training, fine-tuning, retrieval evaluation, and domain-specific question-answering use cases related to agentic AI security, large language model agents, multi-agent systems, threat modeling, autonomous tool use, agent memory, identity risks, human-in-the-loop controls, and mitigation playbooks. The source document focuses on agents based on large language models because LLM-based agents have expanded the scale, autonomy, capabilities, and risks of agentic AI applications.