AI-powered PromptLocker ransomware is just an NYU research project — the code worked as a typical ransomware, selecting targets, exfiltrating selected data and encrypting volumes ◆ Tom’s Hardware

less than 1 minute read

Don’t miss these

Direct Link

Share on

X Facebook LinkedIn Bluesky

You May Also Enjoy

Agent Compromised by Agent To Deploy an Agent

8 minute read

Yesterday (Feb 17, 2026, 12:18AM ET) Cline released an advisory about an unauthorized npm publication. For 8 hours, anyone installing Cline CLI from their of...

Raptor Finds Root Cause of Cline’s Supply-Chain Compromise

2 minute read

Edit (2/19 2:30AM ET): This blog post was written during an ongoing investigation. It shows a messy research process. If you want to learn what happened wit...

First Public Confirmation of Threat Actors Targeting AI Systems

4 minute read

Over the past year I’ve been asking people the same question over and over again: when our AI systems are targeted, will you know?

Make Real Progress In Security From AI

1 minute read

I gave a talk at the AI Agent Security Summit by Zenity Labs on October 8th in San Francisco. I’ll post a blog version of that talk here shortly.