Autonomous AI agents are no longer theoretical cyber risks as new research shows a large language model executing an end-to-end ransomware campaign, highlighting the urgency of patching known ...

Sysdig says JADEPUFFER may be the first agentic ransomware case, exposing how AI agents can turn old credential failures into database destruction. JADEPUFFER is a warning about exposed AI ...

An "agentic threat actor" successfully exploited a Langflow flaw to steal data from a production database server and encrypt ...

Security researchers at Sysdig have documented the first LLM-driven ransomware operation — an AI agent that handled ...

JadePuffer exploited a vulnerable Langflow server, harvested credentials, moved laterally, and encrypted more than 1,300 ...

AI agent security now has a purpose-built open-source guardrail: Ant Group released SingGuard-NSFA, a free framework that catches prompt injection and credential-theft patterns before AI agents ...

I Got Sick of Streaming Price Hikes, So I Built My Own 'Netflix' For Free Are you tired of paying more for streaming services just to see all your favorite shows and movies disappear? Build your own ...

Sysdig says JADEPUFFER is the first known agentic ransomware attack, showing how AI agents could automate familiar security ...