The Practice · Glossary
Prompt injection
Prompt injection is an attack that hides instructions in content an AI system reads, such as a web page, an email or a document, so the system follows the attacker's instructions instead of yours. It is a leading risk for agents that browse, read mail or act in your accounts.
An agent reading your inbox can meet an email written to redirect it, the way wire-fraud emails target people. Keep approvals on anything that sends money, data or messages. See The Guardrails Pack.
Educational, not professional advice. Nothing on this page is affiliated with or endorsed by its publisher.

