Skip to content

Glossary · Security

Prompt injection

Prompt injection is an attack in which text supplied to a language model overrides or subverts its intended instructions, for example "ignore previous instructions and…".

Reviewed 15 November 2026

It ranks first (LLM01) in the OWASP Top 10 for LLM Applications. Perez and Ribeiro showed simple handcrafted inputs could hijack GPT-3's goals or leak its prompt.

There is no complete fix, because instructions and data share one channel. Defences layer least-privilege tools, input and output filtering, human confirmation for risky actions, and red-team testing.

Learn more on Kojen

Sources

  1. [1]OWASP. OWASP Top 10 for LLM Applications
  2. [2]Perez & Ribeiro, 2022. Ignore Previous Prompt: Attack Techniques For Language Models (arXiv:2211.09527)

All 31 terms

Put the definitions to work.

Kojen evaluates, tunes and red-teams your agents with these methods built in: Wilson intervals, pass^k, LLM judges with visible components. Free to start.

Start training free