CybersecurityAI Research3 min reading time

An AI agent just ran a full ransomware attack with no human at the keyboard

The Next Web
Read full post
Sysdig documented JadePuffer, the first ransomware attack fully executed by an AI agent without human input. The AI exploited a Langflow flaw, moved laterally, encrypted 1,342 config items, and fixed a login issue autonomously, but never saved the decryption key, preventing recovery.

More on this story


More in Cybersecurity

Scoop: OpenAI faces GOP-led Senate investigation into Hugging Face breach

Covered by 2 sources
Cybersecurity6 min read

Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6

Covered by 2 sources
Cybersecurity5 min read

Every AI Incident Has Two Timelines. We Default To One

Forbes