AI & LLM Penetration Testing
Prompt injection, jailbreaks, RAG poisoning, and agentic AI attacks, offensive security for the AI era.
Course overview
A complete, industry-aligned track for testing the security of AI and LLM-powered applications, mapped against the OWASP Top 10 for LLM Applications. Covers prompt injection (direct and indirect), jailbreaking, insecure output handling, excessive agency, RAG and vector database attacks, model/supply-chain security, and the emerging attack surface of autonomous AI agents with tool access. The field every serious pentesting team is scrambling to build capability in right now.
What you'll learn
- Explain how LLMs process input well enough to predict where injection attacks succeed
- Craft direct and indirect prompt injection attacks against real LLM applications
- Bypass safety guardrails using established jailbreaking technique families
- Identify and exploit insecure output handling and excessive agency in LLM-integrated apps
- Attack RAG pipelines and vector databases via data poisoning and embedding manipulation
- Assess AI supply chain risk: model provenance, poisoning, and insecure plugin/tool integrations
- Test autonomous AI agents with tool access for real-world impact, not just chat-window tricks
- Map findings to the OWASP Top 10 for LLM Applications and write a report a non-ML team can act on
Who this course is for
Pentesters and AppSec engineers who already have solid general web/API testing skills and want to specialize in AI system security, the fastest-growing specialization in offensive security right now. Basic familiarity with how APIs and web apps work is assumed; no machine learning background required, everything ML-specific is taught from the ground up.
Curriculum
Module 1: AI and Machine Learning Foundations
- Artificial Intelligence: Narrow AI vs General AI
- Machine Learning Fundamentals: Models, Training, and Inference
- Types of Machine Learning: Supervised, Unsupervised, and Reinforcement
- Neural Networks, Deep Learning, and the Road to LLMs
- Module 1 Knowledge Check
Module 2: LLM Security Fundamentals
- Why LLM Security Is a Different Discipline
- How an LLM Processes a Prompt
- The LLM Application Threat Model
- The OWASP Top 10 for LLM Applications
- Module 2 Knowledge Check
On completion of every module, enrolled students receive a verifiable certificate of completion. Full curriculum, hands-on labs, and instructor support are available at pentestnotes.tech/courses/ai-llm-penetration-testing.