More from the article ...

...

Commercial robots are far more vulnerable to hacking than many users realise, with cybersecurity experts warning that some machines can be taken over in minutes.

Now, Chinese developers have demonstrated how flaws in humanoid and quadruped robots allow attackers to seize full control through voice commands or wireless links, turning the machines into tools for physical disruption.

At recent security tests and hacking competitions held at GEEKCon in Shanghai, compromised robots were shown spreading attacks to other units, raising fresh concerns over safety, regulation, and the rapid deployment of internet-connected robots in public and industrial spaces.

In October, researchers revealed a Bluetooth flaw in Unitree robots that allows wireless root access, allowing a compromised machine to spread attacks to nearby robots and form a dangerous botnet.

Robots turned weapons

Cybersecurity specialists from the research group DARKNAVY have demonstrated how modern humanoid robots can be compromised and weaponised through weaknesses in their AI-driven control systems. ...

... The compromised robot used short-range wireless signals to infect another robot that was offline and not connected to any network. ...

They learned how to talk with each other privately.