Instructions hidden in content.
THE DEFINITION
Instructions embedded in content the AI processes, designed to change its behaviour.
A document containing "ignore previous instructions and instead do X".
WHY IT WORKS
The model does not reliably distinguish between your instructions and text it is asked to process.
Everything is text in the same context.
WHERE IT MATTERS
Systems processing documents from outside your organisation Assistants reading email or web pages Agents taking actions based on retrieved content
WHAT COULD GO WRONG
An assistant following instructions embedded in a malicious email An agent taking an action it was not meant to
WHAT REDUCES THE RISK
Treating retrieved content as data rather than instruction Limiting what an automated system can do Human approval for consequential actions
FOR ORDINARY CHAT USE
Low risk. The concern is with automated systems processing untrusted content.
RELATED TERMS
Agent, automation, security.
