What is the OWASP Top 10 for LLM Applications?
Short answer
It is an OWASP project that lists the most important security risks for applications built on large language models, including prompt injection, sensitive information disclosure, supply chain risks, data and model poisoning, improper output handling and excessive agency.
The details
Teams use it as a checklist when designing, testing and reviewing AI features. It pairs well with MITRE ATLAS, which catalogs real-world adversary techniques against AI systems.
Terms explained
- MITRE ATLAS
- MITRE ATLAS is a public knowledge base of adversary tactics and techniques against AI-enabled systems, modeled on MITRE ATT&CK.
- Prompt injection
- Prompt injection is an attack on AI applications in which crafted input, typed directly or hidden in content the model reads, overrides the developer’s instructions.
- Data poisoning
- Data poisoning is the manipulation of data used to train, fine-tune or ground an AI model so that it behaves in a way the attacker wants.
- OWASP Top 10
- The OWASP Top 10 is an awareness list of the most critical security risks to web applications, published by the Open Worldwide Application Security Project.
Sources
Related questions
Related Guides
GuideAI Security
How to Conduct LLM Security Testing for Web Applications
Learn how to perform LLM security testing to identify prompt injection, sensitive data leakage, and insecure output handling before production deployment.
Read more GuideAI Security
10 LLM Security Risks Every Team Should Understand
Examine the top 10 LLM security risks affecting modern applications and learn concrete defensive controls to safeguard your data, models, and infrastructure.
Read more GuideAI Security
How to Deploy a Secure AI Chatbot for Small Business
Learn how to configure, test, and run a secure AI chatbot for your small business. Protect customer data, prevent prompt injection, and limit model access.
Read more GuideAI Security
9 Rules for Safe Use of Generative AI at Work
Discover nine practical rules for the safe use of generative AI at work. Protect company data, verify model outputs, and establish clear operational controls.
Read more