See how meta-hacking got Microsoft Copilot to snitch on itself, exposing CoSnitch, a one-click flaw that silently exfiltrates data.

Learn how to mitigate risks tied to a legacy Entra ID endpoint that undermines Smart Lockout, allowing attackers to confirm valid passwords even on MFA-protected accounts.

With access to Jira, Confluence, Microsoft 365, Google Workspace, Slack, and more, RovoBlast shows how a single link turns AI permissions into a low-friction path for data exposure.

Explore the risks of AI assistant share links and their potential to expose sensitive data.

Dolphin X, a new Windows stealer and remote access trojan, targets hundreds of applications from browsers to crypto wallets and includes an AI Profiler that helps attackers zero in on victims.

Explore the HuggingFace security breach involving an autonomous AI attacker and learn essential strategies to protect your org from similar threats.

AI chatbots widen the attack surface. We took over one to steal data and gain toeholds for launching campaigns.

Discover how Varonis Threat Labs created Breach at the Beach, a unique Entra ID training experience. Enhance your cybersecurity skills through hands-on learning with this CTF.

Varonis Threat Labs deployed MySQL honeypots across GCP, AWS, and Azure. Only GCP was compromised. Here’s what it means for cloud database security.

Varonis Threat Labs discovered SearchLeak, a critical vulnerability chain in Microsoft 365 Copilot Enterprise that allows an attacker to steal sensitive data — MFA codes, email messages, meeting details, and private organizational files — with a single click.

We built an AI agent and put it through four phishing simulations to reveal critical security gaps and offer solutions to protect your organization's data.

GitHub's breach, caused by a malicious VS Code extension, exposed 3,800 internal repositories. Learn how to secure your environment.