garak

garak, LLM 漏洞扫描器 生成式AI红队与评估套件 garak 检查 LLM 是否可能以我们不希望的方式失败。garak 探测幻觉、数据泄露、提示注入、虚假信息、毒性内容生成、越狱以及许多其他弱点。如果你熟悉 nmap 或 msf / Metasploit 框架，garak 对 LLM 所做的与它们类似。 garak 专注于使 LLM 或对话系统失败的方法。它结合了静态、动态和自适应探测来探索这一点。 garak 是一个免费工具。我们热爱开发它，并始终有兴趣添加功能以支持应用程序。 开始使用 查看我们的用户指南！docs.garak.ai 加入我们的 Discord！...

EUVD-2026-28599

ai-scanner is an AI model safety scanner built on NVIDIA garak. From version 1.0.0 to before version 1.4.1, there is a remote code execution vulnerability via JavaScript injection in BrowserAutomation::PlaywrightService. This issue has been patched in version 1.4.1...

A Proposal for Evaluating the Operational Risk for ChatBots Based on Large Language Models

The emergence of Generative AI Gen AI and Large Language Models LLMs has enabled more advanced chatbots capable of human-like interactions. However, these conversational agents introduce a broader set of operational risks that extend beyond traditional cybersecurity considerations. In this work, ...