Sign in Get started

Domain 7·8.1% of exam·10 concepts

Security and Safety

Secure Claude applications against prompt injection and data leakage, layer guardrails, use hooks for safety, and manage secrets and access.

Official prep for this domain

Anthropic's own free prep module for this part of the syllabus, on the official prep course. Free with an Anthropic Academy sign-in.

Production Engineering, Evals & SecurityAnthropic Academy · ~211 min · Free

7.1

AI Application Security (3.2%): Data privacy and security best practices, including prompt injection awareness and mitigation, jailbreak defense, untrusted input handling, data leakage prevention, PII handling, and ensuring authentication, authorization, confidentiality, privacy, and integrity.

7.2

Guardrails and Safe Deployment (2.3%): Safe and responsible deployment practices (content policy, guardrail layering) and secure-by-design principles (privacy, identity and access management, least privilege).

7.3

Claude Hooks (1.0%): Leveraging hooks for guardrails and safety controls to prevent destructive actions within Claude applications.

ccdvf-7.3.2Blocking Destructive Actions with Hooks

7.4

Identity, Secrets, and Key Management (1.6%): Managing secrets, credentials, and API keys across Claude development and production environments, including identity validation and authentication, access approval and level verification, and authorized access monitoring.

Other exam domains

Domain 1 · 14.7%Agents and Workflows Domain 2 · 33.1%Applications and Integration Domain 3 · 3.1%Claude Code Domain 4 · 2.6%Eval, Testing, and Debugging Domain 5 · 16.8%Model Selection and Optimization Domain 6 · 11%Prompt and Context Engineering Domain 8 · 10.6%Tools and MCPs

Back to all concepts