Secure applications built on large language models and tool-using AI agents, through hands-on hardening labs in a simulated environment.
Organizations are connecting large language models to internal data, business systems and tools that act on their behalf. Each connection creates a path an attacker can use, often through nothing more than text the model reads.
This program teaches application security engineers and developers how those attacks work and how to design against them. In each lab, learners take the role of the engineer securing a fictional company’s AI applications, from a support assistant through a retrieval-augmented system to a tool-using agent: they review its design and configuration, choose and apply controls, and verify that the controls hold.
The program is aligned to the OWASP Top 10 for LLM Applications and MITRE ATLAS, and covers Domains 2 and 3 of the IIAS Body of Knowledge in depth.
Award: learners who complete every module, pass every knowledge check and pass every graded lab receive the certificate for LLM and Agentic Application Security, with 12 continuing education (CE) hours. Each certificate has a unique ID and QR code that anyone can verify on the IIAS portal.
Format: self-paced. Each module has a video lesson and a knowledge check; graded labs run inside each lab lesson, in your browser.
Curriculum
- 7 Sections
- 13 Lessons
- Lifetime
- Module 1: Architecture of LLM applications2 Items
- Module 2: Prompt injection3 Items
- Module 3: Output handling and downstream risk3 Items
- Module 4: Retrieval-augmented generation security3 Items
- Module 5: Agents, tools and excessive agency3 Items
- Module 6: Guardrail architecture3 Items
- Module 7: Secure development and deployment3 Items
Requirements
- Working knowledge of web application security, such as the OWASP Top 10
- Ability to read code and use APIs; Python experience is helpful
- AI Security Fundamentals, or equivalent understanding of LLM concepts
Features
- Contain direct and indirect prompt injection through application design
- Identify and fix insecure output handling and downstream injection risks
- Design least-privilege tool permissions and approval steps for AI agents
- Secure retrieval-augmented generation pipelines against poisoning and data leakage
- Design, implement and evaluate layered guardrails
- Threat model an LLM application using OWASP and MITRE ATLAS references
Target audiences
- Application security engineers and security architects
- Software developers building LLM-based features or agents
- Penetration testers extending into AI applications
- Product security and platform engineering teams





