Domain 7 · 9.0% of the CCDV-F exam
Security and Safety
Build Claude applications with secure data handling, layered guardrails, safe tool execution, and controlled identity, secrets, and access management.
Task statements
- 7.1 · 3.0%
AI Application Security
Protect Claude applications from prompt injection, jailbreaks, untrusted input, data leakage, and unauthorized access while preserving confidentiality, privacy, and integrity.
- 7.2 · 2.0%
Guardrails and Safe Deployment
Apply layered guardrails and secure-by-design practices to deploy Claude applications safely, with privacy, identity, access control, and least privilege.
- 7.3 · 2.0%
Claude Hooks
Use Claude hooks to enforce guardrails, validate tool activity, and prevent destructive or unauthorized actions in Claude applications.
- 7.4 · 2.0%
Identity, Secrets, and Key Management
Manage identities, credentials, secrets, and API keys securely across Claude development and production environments.
Build exercises
Threat-model a Claude application
7.1 · Intermediate · 30 minutes
- Identify untrusted inputs.
- Find potential prompt injection paths.
- Identify sensitive data exposure.
- Apply authentication and authorization boundaries.
Design layered guardrails
7.2 · Intermediate · 30 minutes
- Identify safety boundaries.
- Apply multiple guardrail layers.
- Reduce permissions using least privilege.
- Protect sensitive operations.
Add a safety hook
7.3 · Intermediate · 30 minutes
- Identify a destructive tool action.
- Define the condition required before execution.
- Block unsafe actions with a hook.
- Combine hooks with authorization controls.
Secure Claude credentials
7.4 · Intermediate · 30 minutes
- Identify secrets and credentials.
- Separate authentication from authorization.
- Apply least privilege.
- Define secure access monitoring.