Securing AI Agents: How to Prevent Hidden Prompt Injection Attacks
Recognise indirect prompt injection in material an agent reads. Trap recognition only; not anonymisation or disclosure.
About this selection
T12-L02: See how material an agent reads can redirect its task, so you can recognise instructions disguised as source content. Recognition does not guarantee prevention and does not replace anonymisation or disclosure.
Linked by topic; a curriculum association does not certify the full video. Check the source date and compare technical instructions with current official documentation.