HackMyPC
Labs only
AI Security Level 1

Prompt Injection Primer

Understand why untrusted instructions can manipulate AI workflows.

0%
progress
MEDIUMWALKTHROUGH180 XP
Task 1

Instruction hierarchy

AI applications should separate trusted system instructions from untrusted user or document content.

What attack tries to override trusted AI instructions with untrusted text?
TEXT ยท 15 XP
Lab

This room does not need a machine.