Track 15: Frontier and Advanced
AI Security: Prompt Injection, OWASP LLM Top 10 & Guardrails
15 lessons
Track 15: Frontier and Advanced, Agent Security and Red Teaming
Agent Defences That Hold Against Prompt Injection
Apply design patterns that limit what an injected prompt can do.
Get notified on YouTube Udemy certificate: coming soon
Course
AI Security: Prompt Injection, OWASP LLM Top 10 & Guardrails
Udemy: coming soon
Tools
- NeMo Guardrails (open-source, free)
- Guardrails AI (open-source, freemium)
Watch first
Then try
- MCP Security Lab: Tool Poisoning, Tokens, OAuth Scopes
- Red-Team Agents With PyRIT, garak and promptfoo
In this module
- How Agents Get Attacked: The Risky Combination
- Agent Defences That Hold Against Prompt Injection
- MCP Security Lab: Tool Poisoning, Tokens, OAuth Scopes
- Red-Team Agents With PyRIT, garak and promptfoo
The course this lesson belongs to