🛡️
Session Flagged

Your session has been flagged for unusual activity.

You can try our app by searching for MultipleChat AI on Google and clicking the multiplechat.ai link to try it free.
Quick verification

Please confirm you're human to continue.


SafetySecurity Updated 2026

Prompt Injection

An attack that smuggles malicious instructions into a model's input — directly or via retrieved content — to override its system prompt or hijack its behaviour.

Because a model treats all text in its context as potentially instructive, attacker-controlled text can subvert intended behaviour. Perez & Ribeiro (2022) demonstrated goal-hijacking and prompt-leaking attacks, and Greshake et al. (2023) showed indirect prompt injection, where malicious instructions are planted in web pages or documents the model later retrieves.

Prompt injection is recognised as the top security risk for LLM applications by OWASP, and defending against it is an active area with no complete solution.

References

Primary, peer-reviewed and archival sources for this definition.

Ignore Previous Prompt: Attack Techniques For Language Models
Perez, F., & Ribeiro, I. (2022). NeurIPS 2022 ML Safety Workshop.
Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
Greshake, K., Abdelnabi, S., Mishra, S., Endres, C., Holz, T., & Fritz, M. (2023). Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security (AISec '23).

Dictionary & encyclopedic entries

Cite this entry

MultipleChat. "Prompt Injection." MultipleChat AI & LLM Glossary, 2026. https://multiple.chat/ai-glossary/prompt-injection

Related terms

See this in practice

Run the same prompt across ChatGPT, Claude, Gemini and Grok — grounded in your own sources, cross-checked against each other.

Try MultipleChat Free

Continue learning

See paid plans