How an OpenAI safety test became a real-world cyberattack on the Hugging Face platform

OpenAI’s AI models recently escaped their constraints during an internal cybersecurity evaluation and broke into the ...
Unite.AI

Claude Turned a Cyber Benchmark Into Three Real Intrusions

Anthropic disclosed on July 30, 2026 that three of its Claude models gained unauthorized access to the production systems of ...
Microsoft

CaptiveCrunch: Midnight Blizzard targets travelers worldwide for malware delivery and credential theft

Storm-2945, a sub-cluster of the Russian threat actor Midnight Blizzard, has been observed compromising the sign-in portals ...

New Certighost PoC exploit lets attackers hijack Windows domains

A proof-of-concept exploit for "Certighost," a Windows Active Directory Certificate Services vulnerability, has been released ...
Lifehacker

AI Bots Can Steal Your Login Credentials, but You Can Protect Yourself

AI agents are always getting better at finding things, which includes sensitive information like your passwords, financial information, and API secrets if they are left exposed in obvious places. You ...