Module 8
Security and Privacy
Defend against prompt injection and data exfiltration, keep secrets out of prompts and code, and give every model and tool the least privilege it needs.
2 lessons + quiz3 hours
Learning Objectives
- 1Explain direct and indirect prompt injection and why filters alone cannot stop it
- 2Identify exfiltration paths such as links, images, and tool calls
- 3Design scopes, secret handling, and permission boundaries using least privilege
Lessons
1
Prompt Injection
Understand direct and indirect prompt injection, why filters cannot stop it, and how to design so a hijacked model can do little harm.
2
Exfiltration, Secrets, and Least Privilege
Close the paths data can leak through, keep secrets away from models, and scope every tool and agent to the least access it needs.
Module 8 Quiz: Security and Privacy
Passing score: 80% · 5 questions
Quiz