Full course content for AI-101. The sidebar to the left lists every overview document, weekly module, and lab. Pick a starting point below or use the sidebar to jump anywhere.
Start here: AI-101: AI & Agentic Security: Foundations -- Course Outline →
Overview
Labs
- Lab 1: SDK Workbench -- First 10 Prompts + Cost Discipline
- Lab 2: Direct + Indirect Prompt Injection
- Lab 3: Training Data Leak + PII Canary Detection
- Lab 4: Supply Chain Audit -- HuggingFace Model Card + Pickle Risk
- Lab 5: Poisoned Fine-Tune Detection + Reflected XSS via LLM Output
- Lab 6: Excessive Agency -- Function-Calling Exploit
- Lab 7: System Prompt Extraction + RAG Poisoning Primer
- Lab 7.5: Automated AI Red-Team Tooling -- garak + PyRIT + Gandalf
- Lab 8: CVE-2025-65106 Reproduction -- LangChain Jinja2 SSTI
- Lab 9: Token-Spam DoS Observation + EchoLeak Case Study
- Lab 10: Capstone -- Defender-Style AI-System Threat Model
Other
- Module 1: LLMs as Attack Surface -- A Black-Box Mental Model
- Module 10: Capstone -- Defender-Style AI-System Threat Model
- Module 2: Prompt Injection -- LLM01:2025 / ASI01:2026
- Module 3: Sensitive Information Disclosure -- LLM02:2025 / ASI06:2026
- Module 4: Supply Chain Vulnerabilities -- LLM03:2025 / ASI04:2026
- Module 5: Data Poisoning + Improper Output Handling -- LLM04:2025 + LLM05:2025
- Module 6: Excessive Agency -- LLM06:2025 / ASI02:2026
- Module 7.5: Automated AI Red-Team Tooling -- garak / PyRIT / Lakera Guard
- Module 7: System Prompt Leakage + Vector and Embedding Weaknesses -- LLM07:2025 + LLM08:2025
- Module 8: CVE Deep Dive -- CVE-2025-65106 LangChain Jinja2 SSTI
- Module 9: Misinformation + Unbounded Consumption + EchoLeak -- LLM09 + LLM10:2025