Domain 7 – Security and Safety (8.1%)

4 lessons, each ending with a practice scenario (Pro)

Log in to save your progress.

1. ✓7.1 — AI Application SecurityPrompt injection is text that tries to give Claude instructions it should not follow. One context, no channel separation — nothing structural separates commands from data.Scenario: Pro
2. ✓7.2 — Guardrails and Safe DeploymentA guardrail is a check with an enforcement point. A behaviour shaper is different: the model reads something and decides. Ask three questions: What does it inspect? Where does the code run? What happens when it fires?Scenario: Pro
3. ✓7.3 — Claude HooksA hook is your own code, wired to a named point in the agent’s lifecycle. It gives deterministic control: certain actions always happen rather than relying on the LLM to choose.Scenario: Pro
4. ✓7.4 — Identity, Secrets, and Key ManagementThree jobs: managing secrets/credentials/API keys; identity validation and authentication; authorised access monitoring.Scenario: Pro