System prompt leakage

System prompt leakage is the unintended disclosure of a model's hidden instructions or configuration to users, often through crafted questions, which can expose business logic, secrets or ways to bypass safeguards.

System prompt leakage sits in the Prompting & context part of the Agentik {OS} glossary, which defines the words used to build and run AI agent systems.

Also called Prompt leakage, Prompt leaking.