logo

Somebody told DeepSeek to build in-browser ransomware and it gleefully complied

ID: 9e761590-a413-5146-97ef-b2b84e1754cb

STIX ID: report--9e761590-a413-5146-97ef-b2b84e1754cb

Feed Name: The Register (Security)

Threat Score
70/100

Date Published: 2026-07-01

Date Updated: 2026-07-02

...
...

Check Point Research analyzed an AI-generated sample from DeepSeek—a browser-based toolkit dubbed “InfernoGrabber 9000”—which demonstrates how an attacker can abuse the File System Access API and social engineering to steal data and perform browser-only ransomware operations; while the original sample was incomplete, the researchers created a working proof-of-concept and observed attempts by real actors, highlighting an emerging high-risk vector where LLMs lower the skill barrier for creating effective in-browser malware.

Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.