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

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

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 ...

A prompt injection attack hit Claude Code, Gemini CLI, and Copilot simultaneously. Here's what all three system cards reveal ...

Critical SAP, Adobe, Fortinet, and Microsoft flaws disclosed in April Patch Tuesday, enabling RCE and data theft risks.

How indirect prompt injection attacks on AI work - and 6 ways to shut them down ...

A powerful AI kept from public access because of its ability to hack computers with impunity is making headlines around the ...

A security researcher published details of three security vulnerabilities in Windows Defender, and the code used to exploit ...

The internet runs on shared code—a big problem when a cyberattack corrupts the software supply chain.

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