As AI agents evolve from chatbots to autonomous systems capable of executing code, browsing the web and making real-world decisions, they introduce powerful opportunities—and serious security risks. In this CyberArk Labs webinar, researchers Shaked Reiner and Nil Ashkenazi reveal what happens when these agents are manipulated by threat actors, exposing vulnerabilities in real-world implementations and emerging frameworks like the Model-Context-Protocol (MCP). Designed for CISOs, directors, and IT security leaders, this session delivers eye-opening research, real attack scenarios and practical advice for understanding and mitigating the new risks posed by AI-driven autonomy—before adversaries exploit them.
Recommended for You
6:49Reimagining Access Management The Threat Landscape
Lavi Lazarovitz reveals how attackers target identity systems—and why it’s time to rethink access management in today’s evolving threat landscape.
‘Plague’ malware exploits Pluggable Authentication Module to breach Linux systems
Understanding the ‘Plague’ Pluggable Authentication Module (PAM*) backdoor in Linux systems ‘Plague’ represents a newly identified Linux backdoor that has quietly evaded detection by traditional...
45:55Scattered Spider Tactics Revealed
CyberArk experts uncover Scattered Spider’s latest identity attacks and review how to detect threats and defend against privilege abuse.
C4 Bomb: Blowing Up Chrome’s AppBound Cookie Encryption
In July 2024, Google introduced a new feature to better protect cookies in Chrome: AppBound Cookie Encryption. This new feature was able to disrupt the world of infostealers, forcing the malware...
Organizations Largely Unprepared to Manage 47-Day TLS Certificates
This research report reveals how IT and security leaders are thinking about shortening TLS certificate lifespans and 47-day certificate management.
Is your AI safe? Threat analysis of MCP (Model Context Protocol)
Unless you lived under a rock for the past several months or started a digital detox, you have probably encountered the MCP initials (Model Context Protocol). But what is MCP? Is this just a...
Poison everywhere: No output from your MCP server is safe
The Model Context Protocol (MCP) is an open standard and open-source project from Anthropic that makes it quick and easy for developers to add real-world functionality — like sending emails or...
33:53AI, Human Behavior and the Identity Security Risks You Can’t Ignore
Learn about identity security trends from the CyberArk 2025 Identity Security Landscape Report and risk reduction guidance.
Unlocking New Jailbreaks with AI Explainability
TL;DR In this post, we introduce our “Adversarial AI Explainability” research, a term we use to describe the intersection of AI explainability and adversarial attacks on Large Language Models...
26:50Pre-Mortem: AI Agents and the Next Major Breach
In this keynote with CyberArk’s Lavi Lazarovitz, learn how AI agents expose new threats and what organizations can learn from these insights.
Agents Under Attack: Threat Modeling Agentic AI
Introduction The term “Agentic AI” has recently gained significant attention. Agentic systems are set to fulfill the promise of Generative AI—revolutionizing our lives in unprecedented ways. While...
Captain MassJacker Sparrow: Uncovering the Malware’s Buried Treasure
Cryptojacking malware—a type of malware that tries to steal cryptocurrencies from users on infected machines. Curiously, this kind of malware isn’t nearly as famous as ransomware or even...
Let’s Be Authentik: You Can’t Always Leak ORMs
Introduction Identity providers (IdPs) or Identity and Access Management (IAM) solutions are essential for implementing secure and efficient user authentication and authorization in every...
How Secure Is Your OAuth? Insights from 100 Websites
You might not recognize the term “OAuth,” otherwise known as Open Authorization, but chances are you’ve used it without even realizing it. Every time you log into an app or website using Google,...
43:10The US Treasury Dept Breach: Analysis of the Attack
Watch this CyberArk Labs webinar for an in-depth analysis of the Dec. 2024 U.S. Treasury cyberattack, its causes and mitigation strategies.
Securing Against Generative AI-powered Security Events
The increasing complexity of generative AI-driven cyberthreats demands a more diligent approach to how organizations detect and respond to these dangers
Prepare for 2025 Cyberthreats with Research Insights from CyberArk Labs
The year 2025 started with a bang, with these cybersecurity stories making headlines in the first few days: New details emerged on a “major” identity-related security incident involving the U.S....
29:48Emerging Threats in Identity Security What You Need to Know
Learn about recent hacks, emerging attack methods, newly identified threats and essential mitigation strategies.
IDC InfoBrief: Industry Playbook for Identity Security | Addressing Human and Machine Identity Trends
Explore an IDC InfoBrief sponsored by CyberArk, revealing the challenges and trends in identity security across industries. Understand the risks and solutions for managing human and machine identities
Teach Yourself Kubiscan in 7 Minutes (or Less…)
While Kubernetes’ Role-based access control (RBAC) authorization model is an essential part of securing Kubernetes, managing it has proven to be a significant challenge — especially when dealing...
