Biztonsági szemle

Decades-old IPMI bug leaves thousands of internet-facing servers exposed.

OpenAI's recent AI agent sandbox escape proves traditional security principles matter more than ever: limit access, isolate execution, log everything.

Researchers propose focusing on identification of certain cognitive elements in LLMs that indicate when AI systems may take an unwanted action.

Microsoft patched a high-severity vulnerability earlier this month that allows a threat actor to escalate privileges and compromise an AD environment.

AI is exposing hidden data sprawl, making governance a cybersecurity priority.

Here’s the conversations CIOs and CISOs need to have before the next security incident.

The cybersecurity pioneer discusses the evolution of the CISO role, AI's impact on careers, and why operational resilience is the profession's next frontier.

Attackers used Hermes, an autonomous open source tool, in unrestricted "YOLO mode" to conduct espionage against Thailand's Ministry of Finance.

Does movement between these zones require explicit authorization or can it proceed on implicit trust?

PleaseFix class of flaws makes it easy to socially engineer agentic browsers and highlights weaknesses in how they handle cross-origin requests.