← All Events
trainingbeginnerFeatured
AIHEM Fundamentals: Introduction to Agent Red Teaming
Start your journey into AI agent security. Learn the fundamentals of the AIHEM framework and understand how to identify vulnerabilities in agentic AI systems.
Date & Time
Thursday, February 12, 2026
10:00 AM - 1:00 PM PST
Location
virtual
Price
Free
Capacity
50 seats
AIHEM Framework IntroductionAgent Attack SurfaceBasic Prompt InjectionHands-on Labs
// Speakers
G
Guard0 Security Team
Security Researchers
What You'll Learn
This beginner-friendly training introduces the AIHEM (AI Hacking Educational Module) framework. Perfect for security professionals new to AI agent security.
Session Agenda
Part 1: Understanding AI Agents (30 min)
- What are AI agents?
- How agents differ from traditional LLMs
- The agent security landscape in 2026
Part 2: AIHEM Framework Overview (45 min)
- The five phases of AIHEM
- Reconnaissance techniques
- Vulnerability identification
- Exploitation basics
- Reporting and remediation
Part 3: Hands-on Lab (90 min)
- Lab 1: Setting up your testing environment
- Lab 2: Basic agent enumeration
- Lab 3: Your first prompt injection
- Lab 4: Documenting findings
Prerequisites
- Basic understanding of AI/ML concepts
- No prior security experience required
- Laptop with internet connection
Who Should Attend
- Developers building AI applications
- Security professionals exploring AI security
- IT teams managing AI deployments
- Anyone curious about AI agent vulnerabilities
What You'll Receive
- Access to AIHEM lab environment
- Beginner's guide to agent security (PDF)
- Certificate of completion
- Recording access for 30 days