TweakTown

First 'agentic ransomware' run entirely by a large language model discovered

JadePuffer, the first known 'agentic ransomware', uses an AI agent to run attacks end-to-end and adapt in real time, ...

The ‘first’ AI-run ransomware attack still needed a human

An AI agent carried out the technical execution of a real-world ransomware attack for the first known time, but new details ...

AI agent exploits Langflow in first fully autonomous ransomware attack

has documented what it says is the first ransomware operation carried out from start to finish by an autonomous artificial ...
eWeek

First Known ‘Agentic Ransomware’ Attack Raises AI Security Alarm

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

Jadepuffer: The first AI ransomware attack not only messes up the key

Researchers document the first LLM-controlled ransomware attack. But the AI failed due to basic errors. A warning for admins.