OWASP Top 10 for LLM Applications
The reference list of security risks in LLM applications.
Made by OWASPRed teaming and evaluation
About OWASP Top 10 for LLM Applications
The OWASP GenAI Security Project describes itself as a global community-driven and expert led initiative to create freely available open source guidance and resources for understanding and mitigating security and safety concerns for Generative AI applications and adoption.
The guide covers the most critical security risks facing applications powered by large language models. The OWASP GenAI Security Project's AI Security Solutions Landscape initiative maps solutions for LLM and agentic applications. The landscape directory includes traditional and emerging security controls addressing Generative AI, Agentic and AI Red Teaming.
Drafted from genai.owasp.org · not yet confirmed by OWASP
How it works
OWASP's Top 10 for LLM applications lists the main risks (prompt injection, sensitive information disclosure, supply chain, data and model poisoning, improper output handling, excessive agency, system prompt leakage, vector weaknesses, misinformation, unbounded consumption) with mitigations. Most red teaming tools organize their tests around it.
Reviews
Be the first to review it
AnonymousKnow a team weighing OWASP Top 10 for LLM Applications? Send them this page.