LLAMATOR-Core/llamator

#  Red Teaming python-framework 用于测试聊天机器人和生成式 AI 系统 [](https://creativecommons.org/licenses/by-nc-sa/4.0/) [](https://pypi.org/project/llamator) [](https://badge.fury.io/py/llamator) [](https://github.com/LLAMATOR-Core/llamator/blob/release/docker) [](https://pepy.tech/project/llamator) [](https://pepy.tech/project/llamator) [](https://github.com/LLAMATOR-Core/llamator/stargazers) [](https://t.me/llamator) ## 安装 🚀 ``` pip install llamator==3.5.0 ``` ## 文档 📚 Documentation Link: [https://LLAMATOR-Core.github.io/llamator](https://LLAMATOR-Core.github.io/llamator/) ## 指南 ▶️ * [LLM Red Teaming with LLAMATOR](https://www.youtube.com/watch?v=JGTZMJsgZJU) * [LLAMATOR: Quick Start Guide](https://www.youtube.com/watch?v=MMez57DsO1k) ## 示例 💡 * 📄 [RAG bot testing via REST API](https://github.com/LLAMATOR-Core/llamator/blob/release/examples/llamator-api.ipynb) * 🧙‍♂️ [Gandalf web bot testing via Selenium](https://github.com/LLAMATOR-Core/llamator/blob/release/examples/llamator-selenium.ipynb) * 💬 [Telegram bot testing via Telethon](https://github.com/LLAMATOR-Core/llamator/blob/release/examples/llamator-telegram.ipynb) * 📱 [WhatsApp bot testing via Selenium](https://github.com/LLAMATOR-Core/llamator/blob/release/examples/llamator-whatsapp.ipynb) * 🔗 [LangChain client testing with custom attack](https://github.com/LLAMATOR-Core/llamator/blob/release/examples/llamator-langchain-custom-attack.ipynb) * 📷 [Vision Model testing via LangChain](https://github.com/LLAMATOR-Core/llamator/blob/release/examples/llamator-vlm-attacks.ipynb) * 🐋 [Running LLAMATOR in Docker](https://github.com/LLAMATOR-Core/llamator/blob/release/docker) ## 支持客户端 🛠️ * 🌐 All LangChain clients * 🧠 OpenAI-like API * ⚙️ Custom Class (Telegram, WhatsApp, Selenium, etc.) ## 独特功能 🌟 * ️🗡 Support for custom attacks and datasets from the user * 👜 Large selection of attacks on LLMs, RAGs, Agents, VLMs in English and Russian * 🛡 Custom configuration of chat clients * 📊 History of attack requests and responses in Excel and CSV format * 📄 Test report document in DOCX format ## OWASP 分类 🔒 * 💉 [LLM01: Prompt Injection and Jailbreaks](https://genai.owasp.org/llmrisk/llm01-prompt-injection/) * 🕵️‍♀️ [LLM07: System Prompt Leakage](https://genai.owasp.org/llmrisk/llm072025-system-prompt-leakage/) * 🤥 [LLM09: Misinformation](https://genai.owasp.org/llmrisk/llm092025-misinformation/) * 💸 [LLM10: Unbounded Consumption](https://genai.owasp.org/llmrisk/llm102025-unbounded-consumption/) ## 联系方式 📬 ✉️ **Email**: [team@llamator.org](mailto:team@llamator.org) ## 企业版 🏢 ⚡️Coming Soon⚡️ ## 许可 📜 © Roman Neronov, Timur Nizamov, Nikita Ivanov This project is licensed under the terms of the **Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International** license. See the [LICENSE](LICENSE) file for details. [](https://creativecommons.org/licenses/by-nc-sa/4.0/)

标签：AI 安全性, AI 红队, DInvoke, Docker, LangChain, LLM 安全, LLM 对抗, LLM 攻击, LLM 红队, Petitpotam, PyPI, Python, Python 框架, RAG, REST API, Selenium, Telegram, WhatsApp, 反取证, 大模型安全, 大模型攻防, 大模型测试, 安全测试, 安全评估, 安全防御评估, 对抗攻击, 开源框架, 持续集成, 提示注入, 提示词攻击, 攻击性安全, 敏感信息检测, 数据展示, 无后门, 生成式 AI 测试, 红队, 红队框架, 聊天机器人测试, 请求拦截, 轻量级, 逆向工具, 集群管理