# OWASP Top 10 for LLM applications

The OWASP Top 10 for LLM applications is a list of the ten most critical security risks in apps built on large language models (LLMs). OWASP, the Open Worldwide Application Security Project, publishes it.

## The 2026 list

| ID | Risk | What it is |
| --- | --- | --- |
| LLM01 | [Prompt Injection](/glossary/prompt-injection) | Text that overrides the model's instructions |
| LLM02 | [Sensitive Information Disclosure](/glossary/data-leakage) | Personal or confidential data in outputs |
| LLM03 | [Excessive Agency](/glossary/excessive-agency) | More tools, permissions or autonomy than needed |
| LLM04 | Supply Chain | Compromised third-party models, data or code |
| LLM05 | Data and Model Poisoning | Tampered training or embedding data |
| LLM06 | [Unbounded Consumption](/glossary/denial-of-wallet) | Uncontrolled use that drains budget or capacity |
| LLM07 | [Misinformation](/glossary/hallucination) | False output that appears credible |
| LLM08 | [Hidden Context Exposure](/glossary/system-prompt-leakage) | The system prompt and other hidden context extracted |
| LLM09 | [Vector and Embedding Weaknesses](/glossary/rag-security) | Flaws in embedding storage and retrieval |
| LLM10 | Improper Output Handling | Model output passed on without validation |

## Editions

OWASP revises the list, and the IDs move with it. The 2026 edition came out in August 2026. Against the 2025 list, Excessive Agency rose from sixth to third and Unbounded Consumption from tenth to sixth, and System Prompt Leakage widened into Hidden Context Exposure. So cite the year with an ID. Every edition is on the [OWASP project's site](https://genai.owasp.org/).

## How to use it

Use it as a checklist. For each row, name the control you have and the test that proves it.

## With White Circle

[Control](/products/control) enforces your policies on every input, output and tool call. Coverage includes prompt injection, leaks of confidential data, hallucinations, tool abuse and token drain.

