DeepSeek accidentally built a working ransomware strain, experts note, 'What we are witnessing is a fundamental shift in how novel cyber attacks are born'

DeepSeek.

• DeepSeek connected a theoretical browser flaw to a working attack chain
• The ransomware sample targets Android's photo folder through a fake permission prompt
• Check Point classified 1,383 DeepSeek-linked files as malicious or dangerous

A Chinese AI model accidentally stumbled into a working ransomware technique while trying to satisfy an unrealistic, broad prompt.