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.
Cory Doctorow
Trump has staged an unscheduled, midair rapid disassembly of the global system of trade. Ironically, it is this system that prevented all of America's trading partners from disenshittifying their internet: the US trade representative threatened the world with tariffs unless they passed laws that criminalized reverse-engineering and modding. By banning "adversarial interoperability," America handcuffed the world's technologists, banning them from creating the mods, hacks, alt clients, scrapers, and other tools needed to liberate their neighbours from the enshittificatory predations of the ketamine-addled zuckermuskian tyrants of US Big Tech. Well, when life gives you SARS, you make sarsaparilla. The Trump tariffs are here, and it's time to pick the locks on the those handcuffs and set the world's hackers loose on Big Tech. Happy Liberation Day, everyone!
Lori Roussey, Celia/Irídia
In 2022, CitizenLab contacted a member of the Spanish non-profit Irídia to tell them that one of their members had likely been hacked with Pegasus spyware. The target, a lawyer, had been spied on by the Spanish government in 2020 because he represented a Catalan politician who was in prison. His phone was infected with Pegasus during the COVID-19 lockdown, on the same day he was having an online meeting with other lawyers working on the case. Irídia and the lawyer (Andreu) decided to take the case to court. A few years later, he met with Data Rights and invited them to join forces and bring in partners from across Europe to increase the impact. This collaboration led to the creation of the PEGA coalition in May 2025. This talk goes over the status of the case and work we have done across Europe to bring spyware use in court.
Leonard
The character of drone wars has changed. The large, cumbersome long-range drones have been complemented with small and low-budget drones. Moreover, more and more states are developing, deploying and selling them. Ten years ago at least 50 states were developing them. At the top are USA, Israel, Turkey, China, Iran and Russia. Russia's attack on Ukraine has unleashed a drone war unlike any seen before. In short time the Ukraine has build significant drone production capabilities and announcement that it will increase its own production of quadcopters and kamikaze drones to one million units per year. German defense companies and startups are now promoting a “drone wall on NATO's eastern flank.” Moreover, despite their vulnerability to air defenses, large drones are also being further developed. They are intended to accompany next generation fighter jets in swarms. In this talk, past and current developments are discussed. What are the perspectives now?
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.
Klaus Landefeld
Both within the EU as well as nationally in Germany, there exists a renewed drive to implement data retention, a practice struck down by the ECJ and discontinued in many national legislations. In parallel, cross-border access to stored data has been mandated within the EU as “e-evidence”, and will soon be extended to 90+ countries under the umbrella of the EU cybercrime convention. In principle, all data stored by service providers will be available to law enforcement as part of a criminal investigation. The timing of both initiatives is not coincidental, as access to data naturally relies on the availability of data. The talk will address the state of play on data retention in various legislations, and introduce the practice of cross border access to stored data by law enforcement as well as its shortcomings and threats to privacy and confidentiality.
Andreas family & friends Hamburg, Birgit family & friends Hamburg
Mit den Prozessen im Budapest-Komplex wird ein Exempel statuiert - nicht nur gegen Einzelne, sondern gegen antifaschistische Praxis insgesamt. Die Behauptung einer kriminellen Vereinigung mit Mordabsichten stellt eine absurde juristische Eskalation des staatlichen Vorgehens gegen Antifaschist*innen dar und steht in keinem Verhältnis zu den verhandelten Vorkommnissen. Die Verfahren in dieser Weise zu verfolgen, lässt vor allem auf ein hohes Ausforschungs- und Einschüchterungsinteresse schließen. Mit dieser Prozesswelle und den Repressionen gegen Freund*innen und Angehörige wird antifaschistisches Engagement massiv kriminalisiert und ein verzerrtes Bild von politischem Widerstand gezeichnet - während gleichzeitig rechte Gewalt europaweit zunimmt und faschistische Parteien erstarken. Wir sehen, dass Angriffe auf Rechtsstaatlichkeit und Zivilgesellschaft immer weiter zunehmen. Die Art und Weise, wie gegen die Antifas im Budapest-Komplex und im Antifa-Ost Verfahren vorgegangen wird ist ein Vorgeschmack darauf, wie politische Opposition in einer autoritären Zukunft behandelt werden könnte. Wir sind alle von der rechtsautoritären Entwicklung, von Faschisierung betroffen. Die Kriminalisierung von Antifas als "terroristische Vereinigung" ist Teil einer (weltweiten) Entdemokratisierung und Zersetzung von Rechtsstaatlichkeit.
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.