Clint Kehr

Model Context Protocol (MCP) is changing how AI applications connect to external data and tools. Learn how this open standard works, explore its architecture and deployment models, and build hands-on experience securely connecting AI clients and MCP servers.

AI systems introduce a new class of security challenges that traditional tools aren't designed to detect. In this AI Red Team course, you'll take an attacker’s perspective to explore how large language models (LLMs) can be manipulated through natural language and where AI security defenses can break down.

Agentic AI systems are autonomous, goal-driven assemblies of models and tools that can plan, act, and interact with external systems with limited supervision. This course explains what agentic AI is, how Model Context Protocol enable agent orchestration, and why they introduce new attack surfaces.

CVE-2024-23897 is a critical security flaw affecting Jenkins, a Java-based open-source automation server widely used for application building, testing, and deployment. It allows unauthorized access to files through the Jenkins integrated command line interface (CLI), potentially leading to remote code execution (RCE).

CVE-2024-27198 is a critical vulnerability in JetBrains TeamCity, a Java-based open-source automation server used for application building. This flaw allows remote, unauthorized attackers to circumvent authentication, thereby gaining admin control over the server. All versions of TeamCity On-Premises up to 2023.11.3 are affected.

CVE-2023-27524 is a critical vulnerability in Apache Superset, affecting versions up to 2.0.1. It enables attackers to bypass authentication by exploiting weak or default SECRET_KEY values. Attackers can forge session cookies to gain admin access, leading to potential remote code execution and unauthorized data access.

‍

Confluence suffers from a Broken Access Control vulnerability that affects Data Center and Server versions 8.0.0 to 8.3.2, 8.4.0 to 8.4.2, and 8.5.0 to 8.5.1. Threat actors exploit this vulnerability to obtain administrator access to Confluence servers. Put on your Red Team hat to create your own malicious admin account leveraging this CVE!