100% OFF · FreeIT & Software

AI Threat Modeling: Secure LLM, RAG and Agent Systems

This course contains the use of artificial intelligence. Most AI security material either lists risks or teaches attacks. This course teaches the step in between: the design-time method that turns an AI system into a diagram, a ranked threat list, chosen controls and tests that prove those controls work. One system, three stages. We follow the Northwind Shop Assistant, a fictional online retailer's shopping and support assistant. It starts as a chat assistant on a hosted model, gains retrieval over the product catalog, reviews and order history, and ends as an agent that can issue refunds, apply discount codes and email customers through tools. Each stage adds attack surface, so the threat model grows lecture by lecture, the way real systems do. What the course covers Data-flow diagrams for AI systems, and the trust boundaries that only exist in AI: system prompt, user input, retrieved documents, tool results and model output The OWASP Top 10 for LLM Applications, MITRE ATLAS, NIST AI 100-2 and the OWASP agentic guidance, mapped into one working threat catalog STRIDE per element adapted for AI components, prompt injection as a trust-boundary failure, excessive agency, supply chain and denial of wallet RAG threats: poisoned documents, retrieval manipulation and access control on retrieved data Agent and tool threats: confused deputy, over-broad scopes, tool poisoning, memory manipulation, and human-in-the-loop controls that actually work A simple AI risk score, written risk decisions, controls, guardrails and their limits, and turning threats into test cases Keeping the threat model current in the delivery pipeline, and a report an auditor or customer will accept Seven recorded labs, all with free tools. We diagram in OWASP Threat Dragon, write threats as code with pytm, apply the CSA MAESTRO layers to the agent, rank the threat list in a spreadsheet, and test three controls with promptfoo against a small demo app you can run yourself. The capstone puts the full model, the report and the test evidence together. What you get 43 video lectures with captions, about 4 hours 45 minutes in total A quiz at the end of each of the 9 sections, a 40-question practice test and 3 practical assignments Downloads: an AI threat catalog, a risk scoring sheet, a threat model report template and a worked example, the Threat Dragon models, the pytm script, the promptfoo configuration and the demo app source The course assumes basic security knowledge. No machine learning mathematics and no paid tools are needed.

★ 4.5 rating🌐 English🕒 Listed Nov 19, 2026
AI Threat Modeling: Secure LLM, RAG and Agent Systems – Free Udemy Course

What You'll Learn

  • Data-flow diagrams for AI systems, and the trust boundaries that only exist in AI: system prompt, user input, retrieved documents, tool results and model output
  • The OWASP Top 10 for LLM Applications, MITRE ATLAS, NIST AI 100-2 and the OWASP agentic guidance, mapped into one working threat catalog
  • STRIDE per element adapted for AI components, prompt injection as a trust-boundary failure, excessive agency, supply chain and denial of wallet
  • RAG threats: poisoned documents, retrieval manipulation and access control on retrieved data
  • Agent and tool threats: confused deputy, over-broad scopes, tool poisoning, memory manipulation, and human-in-the-loop controls that actually work
  • A simple AI risk score, written risk decisions, controls, guardrails and their limits, and turning threats into test cases
  • Keeping the threat model current in the delivery pipeline, and a report an auditor or customer will accept

About This Free Course

This course contains the use of artificial intelligence.

Most AI security material either lists risks or teaches attacks. This course teaches the step in between: the design-time method that turns an AI system into a diagram, a ranked threat list, chosen controls and tests that prove those controls work.

One system, three stages. We follow the Northwind Shop Assistant, a fictional online retailer's shopping and support assistant. It starts as a chat assistant on a hosted model, gains retrieval over the product catalog, reviews and order history, and ends as an agent that can issue refunds, apply discount codes and email customers through tools. Each stage adds attack surface, so the threat model grows lecture by lecture, the way real systems do.

What the course covers

  • Data-flow diagrams for AI systems, and the trust boundaries that only exist in AI: system prompt, user input, retrieved documents, tool results and model output
  • The OWASP Top 10 for LLM Applications, MITRE ATLAS, NIST AI 100-2 and the OWASP agentic guidance, mapped into one working threat catalog
  • STRIDE per element adapted for AI components, prompt injection as a trust-boundary failure, excessive agency, supply chain and denial of wallet
  • RAG threats: poisoned documents, retrieval manipulation and access control on retrieved data
  • Agent and tool threats: confused deputy, over-broad scopes, tool poisoning, memory manipulation, and human-in-the-loop controls that actually work
  • A simple AI risk score, written risk decisions, controls, guardrails and their limits, and turning threats into test cases
  • Keeping the threat model current in the delivery pipeline, and a report an auditor or customer will accept

Seven recorded labs, all with free tools. We diagram in OWASP Threat Dragon, write threats as code with pytm, apply the CSA MAESTRO layers to the agent, rank the threat list in a spreadsheet, and test three controls with promptfoo against a small demo app you can run yourself. The capstone puts the full model, the report and the test evidence together.

What you get

  • 43 video lectures with captions, about 4 hours 45 minutes in total
  • A quiz at the end of each of the 9 sections, a 40-question practice test and 3 practical assignments
  • Downloads: an AI threat catalog, a risk scoring sheet, a threat model report template and a worked example, the Threat Dragon models, the pytm script, the promptfoo configuration and the demo app source

The course assumes basic security knowledge. No machine learning mathematics and no paid tools are needed.

Who Should Take This Course

"AI Threat Modeling: Secure LLM, RAG and Agent Systems" is aimed at people who want a practical, structured introduction to it & software. It's a solid fit if you're starting out in it & software and want a guided course rather than piecing tutorials together yourself, if you've tried free YouTube content on the topic and want something more organized, or if you already work in a related area and want a refresher you can finish at your own pace. The verified free coupon makes it a low-cost way to explore the topic while the offer remains active. Since enrollment happens on Udemy itself, access is subject to Udemy's course terms.

Why This Course Is Worth Taking

Our take: this listing earns a spot on DeelCart because the coupon we verified actually brings the price to $0, not just a token discount, and the course carries a rating on Udemy. That combination — real reviews plus a working 100% OFF code — is what we look for before publishing a it & software course. It won't replace hands-on experience or a full degree program, but as a low-risk way to test whether it & software is worth pursuing further, or to pick up one specific skill, the free price tag makes it an easy yes while the coupon lasts.

Pros & Cons

👍 Pros

  • 100% free to enroll via this coupon
  • Lifetime access on Udemy once enrolled, even after the coupon expires
  • Self-paced — no fixed schedule or live sessions to attend

👎 Cons

  • Coupon is time-limited and can expire before you enroll
  • No live instructor support — questions go through Udemy's Q&A, not us
  • Certificate is a Udemy completion certificate, not an accredited qualification
Finished reading? Enroll free now

Grab this course free before the coupon expires.

Frequently Asked Questions

Is "AI Threat Modeling: Secure LLM, RAG and Agent Systems" really free?

Yes — we verified a 100% OFF Udemy coupon for this it & software course before publishing it. Enroll directly on Udemy using the button on this page; no credit card is needed while the coupon is active.

How long will this coupon last?

Udemy coupons typically last 1–3 days or expire after roughly 1,000 enrollments, whichever comes first. If the price on Udemy no longer shows $0 when you click through, the coupon has expired since we last checked it.

Do I keep access after the coupon expires?

Yes. Once you enroll while the coupon is live, "AI Threat Modeling: Secure LLM, RAG and Agent Systems" is yours to keep on Udemy — including any future updates the instructor makes — even after the coupon runs out.

More IT & Software Courses