Track 15: Frontier and Advanced
AI Security: Prompt Injection, OWASP LLM Top 10 & Guardrails
15 lessons
Track 9: LLM Engineering and Production, Security
Agent and MCP Security: Excessive Agency, Tool Poisoning
Lock down an agent's tools and servers.
Get notified on YouTube Udemy certificate: coming soon
Course
AI Security: Prompt Injection, OWASP LLM Top 10 & Guardrails
Udemy: coming soon
Tools
- Model Context Protocol (MCP) SDKs (open-source, free)
Watch first
Then try
In this module
- AI Security Basics and Data Leaks (PII, Secrets, Logs)
- Prompt Injection: Direct and Indirect
- OWASP Top 10 for LLM Applications
- Agent and MCP Security: Excessive Agency, Tool Poisoning
- Guardrail Tools: Llama Guard, NeMo Guardrails, Guardrails AI
- Red-Team Your AI App: garak and PyRIT
The course this lesson belongs to