Shipei Qu, Zikai Xu, Xuangan Xiao
We present a comprehensive security assessment of Unitree's robotic ecosystem. We identified and exploited multiple security flaws across multiple communication channels, including Bluetooth, LoRa radio, WebRTC, and cloud management services. Besides pwning multiple traditional binary or web vulnerabilities, we also exploit the embodied AI agent in the robots, performing prompt injection and achieve root-level remote code execution. Furthermore, we leverage a flaw in cloud management services to take over any Unitree G1 robot connected to the Internet. By deobfuscating and patching the customized, VM-based obfuscated binaries, we successfully unlocked forbidden robotic movements restricted by the vendor firmware on consumer models such as the G1 AIR. We hope our findings could offer a roadmap for manufacturers to strengthen robotic designs, while arming researchers and consumers with critical knowledge to assess security in next-generation robotic systems.
Constanze Kurz, khaleesi, Matthias Marx, Linus Neumann, erdgeist
Das war nicht das Jahr 2025, das wir bestellt hatten.
Johann Rehberger
This talk demonstrates end-to-end prompt injection exploits that compromise agentic systems. Specifically, we will discuss exploits that target computer-use and coding agents, such as Anthropic's Claude Code, GitHub Copilot, Google Jules, Devin AI, ChatGPT Operator, Amazon Q, AWS Kiro, and others. Exploits will impact confidentiality, system integrity, and the future of AI-driven automation, including remote code execution, exfiltration of sensitive information such as access tokens, and even joining Agents to traditional command and control infrastructure. Which are known as "ZombAIs", a term first coined by the presenter as well as long-term prompt injection persistence in AI coding agents. Additionally, we will explore how nation state TTPs such as ClickFix apply to Computer-Use systems and how they can trick AI systems and lead to full system compromise (AI ClickFix). Finally, we will cover current mitigation strategies and forward-looking recommendations and strategic thoughts.
Bernd
A brief history of typographic misbehavior or intended and unintended uses of variable fonts. Nine years after the introduction of variable fonts, their most exciting uses have little to do with what variable fonts originally were intended for and their original promise of smaller file sizes. The talk looks at how designers turned a pragmatic font format into a field for experimentation — from animated typography and uniwidth button text to pattern fonts and typographic side effects with unintended aesthetics. Using examples from projects such as TypoLabs, Marjoree, Kario (the variable font that’s used as part of the 39C3 visual identity), and Bronco, we’ll explore how variable fonts evolved from efficiency tools into creative systems — and why the most interesting ideas often emerge when technology is used in unintended ways.
Erwin Ernst "eest9" Steinhammer, lasii, Daniel, Niklas
Auf der Insel Rügen und in Österreich tut sich was - und zwar neue Chaos Events. Wir möchten über Anforderungen, Herausforderungen, Hürden, Erfahrungen und Glücksmomente aus unserer Sicht der Orga erzählen. Das InselChaos fand im LaGrange e.V. im September 2025 statt und bildet den Auftakt für weitere kreative, informative und chaotische Events auf der Insel Rügen. Das Håck ma’s Castle wird mit etwas Humor auch über Herausforderungen sprechen, welche unter anderem durch dezentrale Teams aus diversen Hackspaces entstehen.
Kohlenpod, kater, Stephan
Aus einem Barwitz wurde ein Projekt! Blumenthal7 ist die letzte vollständig erhaltene Schachtanlage des ehemaligen Steinkohlebergwerks General Blumenthal in Recklinghausen im nördlichen Ruhrgebiet. Nach diversen Startschwierigkeiten ist aus einer im Dornröschenschlaf liegenden Industriebrache ein Projekt geworden, das bereits jetzt einer Vielzahl von Entitäten und Gruppen eine Heimat und einen großen, nahezu grenzenlosen Spielplatz bietet. Begleitet uns gerne beim Power Cycle B7…!
Mike Perry
HostileShop is a python-based tool for generating prompt injections and jailbreaks against LLM agents. I created HostileShop to see if I could use LLMs to write a framework that generates prompt injections against LLMs, by having LLMs attack other LLMs. It's LLMs all the way down. HostileShop generated prompt injections for a winning submission in OpenAI's GPT-OSS-20B RedTeam Contest. Since then, I have expanded HostileShop to generate injections for the entire LLM frontier, as well as to mutate jailbreaks to bypass prompt filters, adapt to LLM updates, and to give advice on performing injections against other agent systems. In this talk, I will give you an overview of LLM Agent hacking. I will cover LLM context window formats, LLM agents, agent vulnerability surface, and the prompting and efficiency insights that led to the success of HostileShop.