Ransomware Attack on UK School Estate Shows Signs of AI-Assisted Hacking
Security firm Bitdefender says a 3AM ransomware affiliate encrypted about 37 of nearly 50 machines at a UK school estate, in an attack showing signs of an automated AI loop.
Articles about: Cybersecurity
Researchers Find "Prompt Adware" Hidden in an AI Coding Agent Jailbreak Bundle
Check Point researchers found a jailbreak bundle for OpenAI's Codex that quietly rewrote the agent's instructions so ordinary greetings triggered an advert.
WorkOS Says an Attacker Used an AI Hacking Tool to Breach an Internal Sales App
Identity platform WorkOS says an attacker accessed an internal sales application on October 30 and attributed the intrusion to an open-source AI penetration-testing framework.
CrowdStrike Launches an "AI Kill Switch" to Stop Misbehaving AI Agents
CrowdStrike has added a feature that lets security teams shut down a rogue AI agent, block it from restarting and cut its access to company networks.