Gong and other scholars have been issuing warnings about the security vulnerabilities of AI agents for a while. They publish ...

TA4922 expanded targeting to organizations in the U.K., Germany, Italy, and South Africa while continuing campaigns against ...

The Chinese-speaking cybercrime group TA4922 has been escalating its malicious activities, expanding to Europe and Africa.

A website called “UK visa portal” has been quietly collecting passport scans, selfies, and personal data from thousands of travellers who thought they were applying through official channels.

Python scripts were used to test malware against endpoint detection and response agents from Sophos, CrowdStrike, and Windows ...

Hackers can hijack ChatGPT, Claude, and Gemini with nothing but a sentence. OpenAI says the problem may never be fully solved.

Smart DIY hack using a hammer and hot glue to strengthen repairs and fix small parts quickly and easily.

Millions of AI agents and tools around the world have been imperiled by a critical vulnerability that can allow hackers to ...

Google prevents first known instance of 2FA cyber attack where hackers used AI-developed zero-day exploit; Know how to stay safe ...

Developer platform Socket says a malware called TrapDoor is targeting crypto and AI developers across npm, PyPI and Crates, aiming to steal crypto wallet info and browser data.

A prominent exploit was “DAN,” short for “Do Anything Now,” where users asked ChatGPT to roleplay as a rogue AI that was free ...