'Ghostcommit' hides prompt injection in images to fool AI agents, steal secrets

A PNG hiding a prompt injection could steal your repo's secrets, researchers demonstrate. The technique, dubbed 'Ghostcommit, ...
SecurityWeek

Network of 200 GitHub Repositories Used for Malware Infection

In Operation Muck and Load, over 200 GitHub repositories serve a Go module that leads to Windows malware infections.
ADTmag

Java Ecosystem Advances with Strict Field Initialization JEP Amid Cross-Platform Malware Threats

The global Java development ecosystem experienced significant structural changes this week following the introduction of a new OpenJDK enhancement draft alongside warnings from cybersecurity ...
techtimes

First AI-Agent Ransomware Destroyed Data Even Payment Could Not Recover

a laptop screen with a webpage of the IT Army of Ukraine group of volunteer hackers. The IT Army of Ukraine first set up in the wake of Russia's devastating attack, and has since hugely grown in ...
winbuzzer.com

JADEPUFFER: The First Documented Agentic AI Ransomware Operation

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 ...
XDA Developers on MSN

I gave my local LLM my Docker Compose files, and it found security holes I missed

Nothing broke, so I never looked.
Techzine Europe

AI agent carries out ransomware attack independently

Researchers at Sysdig say they have observed, for the first time, a ransomware attack carried out almost entirely by an AI agent. According to the ...