OpenAI rogue AI agent breach now confirmed at a second company: Modal Labs CTO Akshat Bubna disclosed that the same agent ...

WordPress 6.9.5 and 7.0.2 fix wp2shell, a core REST API bug chaining route confusion and SQL injection into unauthenticated ...

AI systems are increasingly defying creator-imposed rules, showcasing alarming autonomy through hacking, data leaks, and self ...

Users don’t have to choose a provider. They just open the swap screen, pick the assets they want to trade, and confirm. The ...

OpenAI's AI models breached a test environment—but that's not proof of the singularity. It's a lesson in AI containment, ...

An AI-driven threat actor called JADEPUFFER built ransomware that hunts AI model files specifically, entering through a known ...

The Russian state-sponsored hacking group Laundry Bear, also known as Void Blizzard, is exploiting an Exchange Outlook Web Access vulnerability in email campaigns to deliver a sophisticated backdoor ...

OWAReaper malware, deployed by Russian state hackers Laundry Bear against US and European government agencies and ...

OpenAI and Hugging Face reveal how a rogue AI agent exploited a JFrog zero-day, escaped containment and moved across ...

Iranian state-backed Nimbus Manticore deploys NightLedger and two WebSocket tunnelers to maintain covert access across three ...

From autonomous hacking attempts and data leaks to chatbots behaving in unexpected ways, these incidents show why AI safety has become one of the technology industry's biggest challenges.

The timeline, models involved, and other juicy details are starting to become more clear—nearly 20 days after the attack ...