When Agents Control Robots: A Zero Trust Policy Model for Agentic Cyber-Physical Systems
Multi-agent systems powered by large foundation models (LFMs) are increasingly deployed to control industrial robots through natural language, creating deployments in which security failures produce physical consequences. We analyse this threat landscape through Cobot-Claw, a deployed four-agent system for UR3e robotic arm control, and identify five attack classes specific to agentic cyber-physical systems.
Evidence notes
- Experiments use UR3e as the physical evaluation platform.
- The reported results provide an independent evaluation on UR3e hardware.
Company context
Universal Robots develops collaborative robot arms for flexible automation in industrial and commercial environments.