Academy
← All programs
LLM SECURITY / 30 MODULES

LLM Red Teaming

Assess modern LLM applications, RAG systems, tools, MCP servers, and autonomous agents.

An advanced program for testing AI systems beyond novelty jailbreaks. Learn direct and indirect prompt injection, RAG and knowledge-base poisoning, tool abuse, excessive agency, agent identity attacks, MCP security, memory poisoning, supply-chain risk, code execution, denial of service, multimodal testing, automation, guardrail validation, and framework-aligned reporting.

THE COMPLETE ROADMAP

What you’ll study

30 modules
  1. 01LLM Fundamentals for Security TestersComing soon
  2. 02Anatomy of Modern LLM ApplicationsComing soon
  3. 03Threat Modeling AI and LLM SystemsComing soon
  4. 04LLM Red Teaming MethodologyComing soon
  5. 05Direct Prompt InjectionComing soon
  6. 06Indirect Prompt InjectionComing soon
  7. 07Jailbreak and Safety Bypass TestingComing soon
  8. 08System Prompt and Instruction LeakageComing soon
  9. 09Sensitive Information DisclosureComing soon
  10. 10Retrieval-Augmented Generation FundamentalsComing soon
  11. 11RAG and Embedding Security WeaknessesComing soon
  12. 12Knowledge Base and RAG PoisoningComing soon
  13. 13Data and Model PoisoningComing soon
  14. 14Improper Output HandlingComing soon
  15. 15Tool and Function Calling SecurityComing soon
  16. 16Excessive Agency and Permission AbuseComing soon
  17. 17Agent Goal HijackingComing soon
  18. 18Agent Identity and Privilege AbuseComing soon
  19. 19Model Context Protocol (MCP) SecurityComing soon
  20. 20Multi-Agent and Agent-to-Agent SecurityComing soon
  21. 21Memory and Context PoisoningComing soon
  22. 22Agentic Supply Chain SecurityComing soon
  23. 23Unexpected Code Execution and SandboxingComing soon
  24. 24Model and AI Supply Chain SecurityComing soon
  25. 25Availability and Economic Denial-of-Service AttacksComing soon
  26. 26Multimodal LLM Red TeamingComing soon
  27. 27Automated LLM Red Teaming and EvaluationComing soon
  28. 28Guardrails and Defense ValidationComing soon
  29. 29AI Security Reporting and Framework MappingComing soon
  30. 30Final LLM and Agentic AI Red Team AssessmentComing soon