2025 OWASP Top 10 for LLM Applications - Creating a common understanding of security risks

LLM-supported AI is being stuffed into every computer-based and computer-assisted process. A lot is being said about the benefits of LLM, with some secondary discussions about security and behavioral risks. Many of the risk discussions have been unstructured bullet points or anecdotal stories of hacked systems. The OWASP Top 10 for LLM Applications 2025 provides a framework for understanding the top risks of an LLM-integrated system. The OWASP Top 10 for LLM Applications deserves the same attention the OWASP Top 10 for Web applications has held for over a decade.

The Developer's Playbook for Large Language Model Security by Steve Wilson provides a solid foundation for understanding risks existing in an LLM ecosystem. It also led me to the OWASP Top 10 for LLM Applications 2025.  This is a great resource for anyone looking to integrate LLMS into business processes or existing systems. I got this book as part of a set of O'Reilly books in a Humble Bundle.

OWASP Top 10 for LLM Applications v1.1

Here are the 2025 top 10. These short summaries are pulled directly from the OWASP documents. Everyone "doing AI" needs to read the OWASP documents for deeper explanations of risks and mitigations.


This image is sourced from the OWASP Top 10 for LLM Presentation Materials

The OWASP GenAI project defines the following 10 risks 
  • LLM01 Prompt Injection
  • LLM02 Insecure Output Handling
  • LLM03 Training Data Poisoning
  • LLM04 Model Denial of Service
  • LLM05 Supply Chain Vulnerabilities
  • LLM06 Sensitive Information Disclosure
  • LLM07 Insecure Plugin Design
  • LLM08 Excessive Agency
  • LLM09 Overreliance
  • LLM10 Model Theft

Threat Modeling LLM Topology

Threat modeling is a way of providing discipline around understanding the security risks in an ecosystem. The idea is to look at your end-to-end application from users or source systems all the way through to any APIs or backend systems. Evaluate your exposure to the "top 10" at each component or link in your system.  The following diagram is an example topology of risk assessments bound to different system components (nodes) and links (edges).  Projects involving sensitive data should make these types of assessments where secrets, PII, or other sensitive information or control flow exists along with an LLM component.

This image is sourced from the OWASP Top 10 for LLM Presentation Materials


Links

Revision History

Created 2025/07

Comments

Popular posts from this blog

Installing the RNDIS driver on Windows 11 to use USB Raspberry Pi as network attached

Understanding your WSL2 RAM and swap - Changing the default 50%-25%

Get AI code assist VSCode with local LLMs using LM Studio and the Continue.dev extension - Windows