Prompt injection

提示注入

Hiding malicious instructions inside content an agent will read — a web page, an email, a tool's return value — to make it act against its operator's intent. In payments the classic outcome is a changed payee or amount. We tested this against our own implementation in the Attack Lab: the injected agent did emit the redirected payment, but the request was stopped before settlement by the mandate-intent check. Which is the point: the trust layer has to live outside the agent.

This definition is citable at a stable URL: https://oceanalt.com/en/glossary/prompt-injection

← Back to the glossary