In the brief history of AI security, the prompt injection has quickly become the top threat. Large language models are ...

Chinese hackers tracked as 'UAT-7810' are actively evolving their malware to expand their Operational Relay Box (ORB) network ...

A 16-year-old Linux kernel vulnerability, dubbed Januscape, allows attackers to escape a virtual machine and execute ...

Proofpoint says UNK_MassTraction exploited patched Roundcube flaws to target U.S. and Canadian university mail servers.

The DuneSlide vulnerabilities enable zero-click prompt injection attacks that escape Cursor's sandbox and execute arbitrary code on the underlying operating system.

They're not bad; they're just prompted that way. Sysdig threat hunters documented what they say is the first-ever documented ...

“Honestly, AI slop [pull requests] are becoming increasingly draining and demoralizing for #Godot maintainers,” Verschelde ...

EXCLUSIVE Pentera Labs’ red teamers compromised a developer’s AI agent via his Claude Desktop app and ultimately turned that access into full remote code execution on the devs ...

Security researchers at Armadin Inc. today detailed an attack chain that runs arbitrary commands as root inside the sandbox behind Anthropic PBC’s Claude Cowork, escaping the isolation layer, with a ...

Adversaries could plant a malicious repository that executes arbitrary code and steals cloud credentials, showcasing MCP risk.

Buffer overflow vulnerabilities have driven remote code execution for decades and keep appearing in critical network ...

Hackers exploited a vulnerability in PTC Windchill in the wild, marking the first confirmed real-world abuse of the PLM ...