Biztonsági szemle

Attackers can take control of agents through malicious instructions hidden in content supplied to AI browsers, and there's no simple fix for the threat.

AI browsers from top vendors remain vulnerable to prompt injection attacks despite multiple security guardrails, according to new research.

CSS was once just about design. Now researchers warn it's powerful enough to exfiltrate data from webmail — and some vendors aren't prepared.

Researchers are calling attention to the risks inherent in automated network device provisioning, using a world-leading device manufacturer as a case study.

Google has fixed the issues, which exploited a trust boundary between two AI agents with different privilege levels to trigger automation that could compromise the supply chain.

Organized crime is convincingly scamming at scale, making billions thanks to AI-enabled voice cloning, deepfake real-time video overlays, LLM-driven persona management, and automated translation.

Unitel, Angola's dominant mobile operator, continues to recover from a cyberattack that caused outages the day of the government-owned telco's public offering.

The attacks use diverse social engineering lures and rotating payloads to deliver ScreenConnect for persistent remote access to compromised networks.

A Google Firebase misconfiguration lets users of tl;dv, an AI meeting tool, query any other users' meeting information and potentially join calls.

Newer social engineering techniques help attackers ignore entrenched security controls and limit the evidence they leave behind.

Over the weekend, the vendor discovered another vector of authentication bypass CVE-2026-18577 that gives attackers administrator access.

Researchers dug into the root of the problem with the goal of promoting industry collaboration on improved protective measures.