← Back to the AI Glossary 📖 Prompting & Interaction

Prompt Injection

An attack where malicious instructions are hidden inside content an AI is asked to process (a document, webpage, or email) to try to hijack its behaviour.

It's a growing concern as AI agents read and act on more external content automatically — always be cautious about what an AI-powered tool is allowed to read and act on unsupervised.
One of 60 free AI glossary terms
Plain-language definitions for the AI jargon you'll actually run into — no email needed, ever, for this section.
Browse the Full Glossary →
More in Prompting & Interaction
Few-Shot Learning
Giving an AI a few examples of the task and desired output format before asking it to do t...
Persona / Role Prompting
Asking an AI to respond as if it were a specific type of expert, character, or perspective...
Jailbreak
A prompt specifically crafted to trick an AI model into ignoring its safety guidelines and...
Hallucination
When an AI confidently states something false or fabricated as if it were fact — a made-up...