Unitree is among the highest-volume makers of commercial robots, and their newest humanoid platforms ship with multiple control stacks and on-device AI agents. If the widespread, intrusive presence of these robots in our lives is inevitable, should we take the initiative to ensure they are completely under our control? What paths might attackers use to compromise these robots, and to what extent could they threaten the physical world?

In this talk, we first map the complete attack surface of Unitree humanoids, covering hardware interfaces, near-field radios and Internet-accessible channels. We demonstrate how a local attacker can hijack a robot by exploiting vulnerabilities in short-range radio communications (Bluetooth, LoRa) and local Wi-Fi. We also present a fun exploit of the embodied AI in the humanoid: With a single spoken/text sentence, we jailbreak the on-device LLM Agent and pivot to root-priviledged remote code execution. Combined with a flaw in the cloud management service, this forms a full path to gain complete control over any Unitree robot connected to the Internet, obtaining root shell, camera livestreaming, and speaker control.

To achieve this, we combined hardware inspection, firmware extraction, software-defined radio tooling, and deobfuscation of customized, VM-based protected binaries. This reverse engineering breakthrough also allowed us to understand the overall control logic, patch decision points, and unlock advanced robotic movements that were deliberately disabled on consumer models like G1 AIR.

Takeaways. Modern humanoids are networked, AI-powered cyber-physical systems; weaknesses across radios, cloud services, and on-device agents could allow attackers to remotely hijack robot operations, extract sensitive data or camera livestreams, or even weaponize the physical capabilities. As robotics continue their transition from controlled environments to everyday applications, our work highlights the urgent need for security-by-design in this emerging technology landscape.