The new “agentjacking” attack takes almost no real hacking ability to pull off. It's predicated on pulling a public ...
Tenet Security researchers reveal how new “agentjacking” attacks could trick coding agents into executing arbitrary code ...
A threat actor tracked as DriveSurge has been operating large-scale malware distribution campaigns using ClickFix and FakeUpdates techniques on compromised sites. Thousands of websites have been ...
Chrome's WebMCP guidance warns that AI agents can be manipulated through the tools they are built to trust.
Microsoft details AutoJack exploit chain targeting AutoGen Studio MCP WebSocket in pre-release builds, enabling ...
Three popular plugins served malicious JavaScript through a compromised CDN.
A poisoned npm package infected 140+ projects with a hidden payload. This report highlights how to detect, hunt, and defend ...
An unpatched SQL injection vulnerability in the Ghost content management system has been weaponized in an active, large-scale cyberattack that has compromised more than 700 websites worldwide — ...
Security researchers from GoDaddy found a cheeky new malware campaign that used comments made by Steam Community accounts as command-and-control (C2) infrastructure. Here is how the attack plays out: ...
Look to these key metrics and benchmarks to evaluate the performance, capability, reliability, and safety of your AI models ...