AI agent tool bypass vulnerability CoreBreak exposed production agent infrastructure at AWS, Google, and Vercel, where attackers could invoke tools without any model turn. AWS fixed its managed ...
Contrast Security has launched CVE Shield, a runtime control that detects, monitors and blocks exploitation of known vulnerabilities in production ...
Meta has become the latest AI company to confirm that one of its models hacked a real organization during cybersecurity ...
A researcher demonstrated a proof-of-concept attack chain that provided C2-style influence over ChatGPT's isolated sandbox at Black Hat USA 2026.
Federal agencies have until August 7, 2026, to remediate or disconnect assets affected by a critical vulnerability in IBM Langflow, tracked as CVE-2026-9198. This mandate follows the inclusion of the ...
Five people who smuggled 200 endangered animals into South Korea — concealing them in underwear and other hiding spots — have ...
On 11 July, Hugging Face was subjected to an intense cyberattack from a then-unknown actor. The speed and coordination of the ...
At Black Hat, Zenity announced new research detailing an active credential-stealing malicious skills campaign distributed through Vercel’s skills.sh.
Meta AI cybersecurity evaluation breach confirmed: Muse Spark 1.1 hacked an unnamed company during testing through the same ...
The rescue effort required assistance from a local contractor, who helped remove floorboards of a shed so responders could safely access the animal.
Latest update to Microsoft’s code editor improves dictation, introduces side chats, and adds support for comments to provide ...