Overview
In this 1-hour course, you’ll explore how attackers target AI agents, MCP servers, and AI-powered applications through prompt injection, insecure tool usage, memory attacks, and API weaknesses. Learn practical AI hacking and security testing techniques to better secure modern AI systems and workflows.
What I will be able to do after this course
- Understand AI agent architectures
- Explore MCP security fundamentals
- Analyse prompt injection attacks
- Identify memory poisoning risks
- Test insecure AI tool integrations
Course Instructor(s)
Dr. Katie Paxton-Fear is a Staff Security Advocate at Semgrep, ethical hacker, AI security researcher, and educator with a PhD in natural language processing and cybersecurity. She specialises in application security, bug bounty research, and practical AI hacking education.
Who is it for?
This course is for application security professionals, AI engineers, penetration testers, developers, and DevSecOps practitioners looking to understand and secure AI agents, MCP systems, and modern AI-powered applications. Familiarity with APIs and AppSec fundamentals is recommended.
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Watch now
Unlock full access