Prompt injection
An attack or accidental instruction that tries to make an AI system ignore its intended rules, reveal data, or misuse tools.
Business example
A malicious instruction hidden in a webpage tells an agent to disclose confidential information when it summarizes the page.
How it works
- 1.Untrusted content enters the model context.
- 2.The content imitates a higher-priority instruction.
- 3.Isolation, least privilege, and confirmation limit the possible impact.
Common misconceptions
Related concepts
Related reading
Sources
Reviewed:
Reviewed by: Javier Chulvi Bernad · LLM Engineer · Madrid