Agentic ProbLLMs：利用 AI 计算机使用与编码智能体的安全研究（39C3 视频与幻灯片）
Agentic ProbLLMs: Exploiting AI Computer-Use And Coding Agents (39C3 Video + Slides) · Embrace The Red
Johann Rehberger 在汉堡 39C3 演讲《Agentic ProbLLMs: Exploiting AI Computer-Use and Coding Agents》，分享针对智能体系统漏洞的安全研究及 Month of AI Bugs 项目，并附大量演示。演讲视频可在 media.ccc.de 观看，英文版已上传至 Embrace The Red YouTube 频道，幻灯片提供 PDF 下载。
正文
当前显示原文，中文全文译文尚未就绪。
It was great to attend the 39C3 - Power Cycles in Hamburg this year. The Chaos Communication Congress was once again packed with great talks, amazing people, awesome events and side quests - and I even got to present!
You can watch the talk with translation options on media.ccc.de.
I also uploaded the English version to the Embrace The Red YouTube channel. I hope it’s interesting and helpful.
The talk is titled “Agentic ProbLLMs: Exploiting AI Computer-Use and Coding Agents” and is about my security research on vulnerabilities in agentic systems and the Month of AI Bugs with lots of demos.
A PDF version of the slides is here.
Looking forward to the next Chaos Communication Congress.
Safe travels back home and Happy Hacking, everyone!