# OWASP LLM Top 10

> A community list of the most significant security risks specific to applications built on large language models.

It exists because the classic web list does not cover this ground. The risks it names — prompt injection, insecure handling of model output, supply-chain problems in models and plugins, sensitive data ending up in a response, excessive permissions granted to an agent — do not map onto injection, broken access control and the rest without losing the thing that makes them distinctive.

Used well, it is a conversation starter rather than a certificate. Walking an architecture against the list surfaces the question that matters — what can this system do when the model is wrong — earlier and more cheaply than finding out in production. Used badly, it becomes a checklist to sign off, which is the failure mode of every list of this kind.

## Related terms

- https://dfieldsolutions.com/en/glossary/prompt-injection.md
- https://dfieldsolutions.com/en/glossary/llm-agent.md
- https://dfieldsolutions.com/en/glossary/data-exfiltration.md
- https://dfieldsolutions.com/en/glossary/owasp-top-10.md

---

Source: https://dfieldsolutions.com/en/glossary/owasp-llm-top-10
DField Solutions — Dunakeszi, Hungary — dezso@dfieldsolutions.com
Booking: see https://dfieldsolutions.com/en/contact