Learning Path

LLM Red Teaming

A progressive path through prompt injection first principles, indirect injection from untrusted data, jailbreaking, system-prompt extraction, and agentic tool-use exploitation.

6 available Start the path
  1. 1 beginner

    LLM Tokens, Context Windows, and the Attack Surface

    How LLMs process text through tokenization, manage context windows, and where these mechanics create exploitable attack surface for red teamers.

  2. 2 beginner

    Prompt Injection from First Principles

    Build a vulnerable LLM chatbot with Ollama, exploit it with direct and indirect prompt injection, then layer defenses to see why it is fundamentally hard.

  3. 3 intermediate

    Jailbreaking: Bypassing LLM Alignment Controls

    A taxonomy of jailbreak techniques: persona attacks, encoding tricks, few-shot poisoning, and multi-turn escalation, with a rubric for scoring bypasses.

  4. 4 intermediate

    Indirect Prompt Injection Through Untrusted Data

    Explore how adversarial content in retrieved documents, emails, and web pages can hijack LLM behavior, from RAG poisoning to cross-plugin attacks.

  5. 5 intermediate

    Tool Use and Agentic Exploitation

    Attack LLM agents through confused deputy problems, tool argument injection, and data exfiltration via tool chains, with hands-on Ollama exercises.

  6. 6 intermediate

    System Prompt Extraction and Defense Hardening

    Techniques for extracting hidden system prompts from LLM applications, and how to harden your prompts against extraction attacks.

All tutorials and learning paths