Hackers are targeting sensitive information stored in the LiteLLM open-source large-language model (LLM) gateway by ...

Dozens of vulnerabilities were discovered recently in the open source electronic medical records platform OpenEMR.

Every secure API draws a line between code and data. HTTP separates headers from bodies. SQL has prepared statements. Even email distinguishes the envelope from the message. The Model Context Protocol ...

This month’s threat landscape is ‘defined by immediate, real-world exploitation rather than just theoretical vulnerabilities,’ says an incident response manager.

Mythos is, on standard benchmarks for coding, logical reasoning, and mathematical problem-solving, the most capable AI model yet built. What has triggered alarm is something rather more consequential ...

CVE-2026-42208 exploited within 36 hours of disclosure, exposing LiteLLM credentials, risking cloud account compromise.

Google has analyzed AI indirect prompt injection attempts involving sites on the public web and noticed an increase in ...

Nearly every major product family needs immediate patching, from Windows to Office to Microsoft Edge, SQL Server, and even ...

The latest monthly Patch Tuesday update from Microsoft landed earlier on 14 April, including two notable zero-day flaws amid a total of over 160 distinct issues, and almost 250 accounting for ...

Security researchers have discovered 10 new indirect prompt injection (IPI) payloads targeting AI agents with malicious ...

News of data breaches is nothing new in 2026, and we’ve seen dozens just since the start of the year. A lot of this comes ...

Update: Revised story and title based on new information linking the attack to North Korean hackers. The Drift Protocol lost at least $280 million after a threat actor took control of its Security ...