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

Post a Comment

Popular posts from this blog

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

Image
I do a lot of my development and configuration via ssh into my Raspberry Pi Zero over the RNDIS connection. Some models of the Raspberry PIs can be configured with  gadget drivers  that let the Raspberry pi emulate different devices when plugged into computers via USB. My favorite gadget  is the network profile that makes a Raspberry Pi look like an RNDIS-attached network device.  All types of network services travel over an RNDIS device without knowing it is a USB hardware connection. A Raspberry Pi shows up as a Remote NDIS (RNDIS) device when you plug the Pi into a PC or Mac via a USB cable. The gadget  in the Windows Device Manager picture shows this RNDIS Gadget connectivity between a Windows machine and a Raspberry Pi. The Problem Windows 11 and Windows 10 no longer auto-installs the RNDIS driver that makes magic happen. Windows recognizes that the Raspberry Pi is some type of generic USB COM device. Manually running W indows Update  or  Upd...
Read more

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

Image
The Windows Subsystem for Linux operates as a virtual machine that can dynamically grow the amount of RAM to a maximum set at startup time.  Microsoft sets a default maximum RAM available to 50% of the physical memory and a swap-space that is 1/4 of the maximum WSL RAM.  You can scale those numbers up or down to allocate more or less RAM to the Linux instance. The first drawing shows the default WSL memory and swap space sizing. The images below show a developer machine that is running a dev environment in WSL2 and Docker Desktop.  Docker Desktop has two of its own WSL modules that need to be accounted for.  You can see that the memory would actually be oversubscribed, 3 x 50% if every VM used its maximum memory.  The actual amount of memory used is significantly smaller allowing every piece to fit. Click to Enlarge The second drawing shows the memory allocation on my 64GB laptop. WSL Linux defaul...
Read more

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

Image
This is about running VSCode AI code assist locally replacing Copilot or some other service.  You may run local models to guarantee none of your code ends up on external servers. Or, you may not want to maintain an ongoing AI subscription. We are going to use  LM  Studio and VS Code.  This was tested on Windows 11 with an RTX 3060 TI with 8GB of VRAM. 8GB really limits the number and size of the models we can use. LM Studio's simple hosting model of 1 LLM and an embedding works for us in this situation.  You want a big card. 8GB is a tiny card. Related blog articles and videos Several related blogs and videos that cover VSCode and local LLMs Blog  Get AI code assist VSCode with local LLMs using Ollama and the Continue.dev extension - Mac Get AI code assist VSCode with local LLMs using LM Studio and the Continue.dev extension - Windows Rocking an older Titan RTX 24GB as my local AI Code assist on Windows 11, Ollama and VS Code YouTube Video  Using loc...
Read more