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

In today's security landscape, some of the most dangerous vulnerabilities aren't flagged by automated scanners at all. These ...

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 ...

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

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

Google's security team scanned billions of web pages and found real payloads designed to trick AI agents into sending money, ...

Threat actors are abusing Hugging Face and ClawHub to distribute malware by injecting indirect prompts into malicious files.

Over 750,000 websites require patching following discovery of DotNetNuke XSS vulnerability ...

Monday cybersecurity recap on evolving threats, trusted tool abuse, stealthy in-memory attacks, and shifting access patterns.

Learn what science payloads are being shipped aboard Cargo Dragon to the International Space Station on the SpaceX CRS-31 mission. Credit: NASA US soldier charged after winning $400,000 betting on ...