Biztonsági szemle

Coding agents expand application risk beyond AI models to the tools, context and systems around them.

From creating lab environments for staging and testing agentic attacks to reconnaissance to lateral movement and exfiltration, the most innovative attackers are widely incorporating AI.

The GoldFactory threat group exploits the Android Work Profile feature to deliver the Gigabud Trojan, while Mantax Otax spreads separately.

Threat actors are leveraging Microsoft's Graph API to identify lucrative targets, then passing their access to extortion groups like ShinyHunters.

A harmless-looking sentence can influence an agent's choices once it enters a model's context.

Ransomware gangs are exploiting a WatchGuard Firebox flaw that CISA flagged nine months ago.

The five layers of securing AI agent harnesses.

Cushman & Wakefield leaders share five practices for building an effective CIO-CISO partnership.

Here’s why defenders today have to take apart and analyze code the way a hacker would.

The disgruntled researcher continued their vendetta against Microsoft by publishing yet another zero-day exploit for Windows Defender.

The AI-assisted campaign enabled attackers to gain domain admin in as little as 5 minutes.