Plain-English AI definitions for legal professionals. For what bars actually require, see the Legal AI Compliance Register.

Prompt injection

Risk and governance Last reviewed 2026-07-01

Definition An attack on AI systems in which crafted text—typed by a user or hidden in a document, email, or web page the system reads—overrides the model's instructions and steers it into unintended behavior.

In more depth

Language models read their operating instructions and the content they are given as one stream of text, so a document, email, or web page an AI tool ingests can smuggle in wording the model treats as a command. Injected instructions can override the vendor's system prompt, pull information the session has access to, or misdirect an AI agent into unintended actions—and the indirect, hidden-in-content form is the harder problem, because the user never sees it. No complete technical fix exists today; practical mitigations include restricting what data and tools an assistant can reach, filtering untrusted content, and keeping human approval in front of consequential actions. For legal teams it is a vendor-diligence question: before pointing a tool at client matter data, ask how it defends against instructions embedded in the material it reads.

Further reading: Wikipedia.

Related terms

About the editor: MHSB Solutions, Research desk. MHSB Solutions is not a law firm. This glossary is educational information, not legal advice.

Educational information, not legal advice. AI terminology and tools change quickly; definitions reflect usage as of the last-updated date. For what bar associations and courts actually require of lawyers using AI, see legalaicompliance.help and consult a licensed attorney in your jurisdiction.