Skip to content
Humanoid Robots Vulnerable to Voice Command Hacks at GEEKCon

Humanoid Robots Vulnerable to Voice Command Hacks at GEEKCon

First seen 27 Dec 2025, 10:01 UTC

Article Content

Browse articles
ThreatCluster AI
ThreatCluster March 12, 2026 at 13:27 UTC

Chinese researchers demonstrated at GEEKCon in Shanghai that humanoid robots can be compromised using voice commands, allowing attackers to take control and potentially spread the infection to other nearby units. This vulnerability poses risks of physical disruption as compromised robots can act as 'Trojan horses' to hijack additional machines.

Start a free Starter trial for enhanced analysis

Ask AI about this cluster

Updated 183d ago How this analysis works

More articles in this cluster (5)

Following this threat?

Track Unitree in your own feed — you're alerted when they show up in new reporting, leak sites or exploitation.

Free account · no card needed