Skip to content
BENIBIX Learn

OWASP Top 10 for LLM Applications

Also known as OWASP LLM Top 10, OWASP Top 10 for LLMs, OWASP GenAI Top 10

A free list of the ten biggest risks in apps built on LLMs.

Think of it like

It is like a list of the ten most common ways burglars get into a house. You check your house against it.

Example

Emma's team checks their new chatbot against the 2025 list. Item LLM06 is about too much power. So they take away the bot's power to give refunds by itself.

Why it matters

It gives builders a shared list of what to test, written by people who see real attacks.

Definition

The OWASP Top 10 for LLM Applications is a free list of the ten biggest risks in apps built on large language models. It comes from OWASP, a group known for its lists of web risks. The 2025 list starts with prompt injection. Next comes leaking private data. It also covers poisoned data, unsafe use of a model's output, agents with too much power, leaked system prompts and runaway costs. Teams use it as a checklist when they build and test an AI app.
The 2025 list, from prompt injection at the top to runaway costs at ten.

Common mistake

Thinking the web Top 10 covers AI apps. The LLM list adds risks a normal web app does not have.

Key takeaways

  1. 1
    Ten top risks. Ranked for apps built on LLMs.
  2. 2
    Free and open. Made by a nonprofit.
  3. 3
    A checklist. Test your app against it.