7.1Intermediate30 minutes
7.1 — Threat-model a Claude application
What you will learn
- Identify untrusted inputs.
- Find potential prompt injection paths.
- Identify sensitive data exposure.
- Apply authentication and authorization boundaries.
← Build Exercises
Domain 7
Security and Safety
4 build exercises to practice the concepts in this domain.
7.2Intermediate30 minutes
7.2 — Design layered guardrails
What you will learn
- Identify safety boundaries.
- Apply multiple guardrail layers.
- Reduce permissions using least privilege.
- Protect sensitive operations.
7.3Intermediate30 minutes
7.3 — Add a safety hook
What you will learn
- Identify a destructive tool action.
- Define the condition required before execution.
- Block unsafe actions with a hook.
- Combine hooks with authorization controls.
7.4Intermediate30 minutes
7.4 — Secure Claude credentials
What you will learn
- Identify secrets and credentials.
- Separate authentication from authorization.
- Apply least privilege.
- Define secure access monitoring.