RAG & Agents
Prompt Injection
Text in untrusted content that the model interprets as instructions, because LLMs have no architectural separation between instructions and data.
Why interviewers ask about it
No prompt-level defence is reliable. Design so a successful injection cannot cause harm: least privilege, drop irreversible capabilities after untrusted reads, enforce limits in code.
Related terms
This term is part of the free AI/ML Engineer interview preparation module - browse the full glossary for every definition.