OWASP Top 10 for LLM Applications
A list of security risks for large language model applications published by OWASP, enumerating the core risk categories facing LLM applications, such as prompt injection, excessive agency and data leakage.
Core Facts
Timeline (last 90 days)
The first edition of the OWASP Top 10 for LLM Applications in 2023 listed Prompt Injection as LLM01, and the 2025 edition still places it first and subdivides it into direct injection and indirect injection.
The OWASP Top 10 for LLM Applications points out that the non-determinism of model behavior is why prompt changes need regression coverage.
In the OWASP Top 10 for LLM Applications, LLM05:2025 specifically discusses "Improper Output Handling," and LLM09:2025 discusses "Overreliance."
The OWASP Top 10 list of risks for large language model applications was first published in 2023 and updated in 2025.
OWASP ranks prompt injection as the top risk among the ten major risks for large model applications.
OWASP has released the OWASP Top 10 for LLM Applications security risk list.
All Facts (6)
OWASP ranks prompt injection as the top risk among the ten major risks for large model applications.
65%UnverifiedThe first edition of the OWASP Top 10 for LLM Applications in 2023 listed Prompt Injection as LLM01, and the 2025 edition still places it first and subdivides it into direct injection and indirect injection.
50%UnverifiedThe OWASP Top 10 for LLM Applications points out that the non-determinism of model behavior is why prompt changes need regression coverage.
50%UnverifiedIn the OWASP Top 10 for LLM Applications, LLM05:2025 specifically discusses "Improper Output Handling," and LLM09:2025 discusses "Overreliance."
50%UnverifiedThe OWASP Top 10 list of risks for large language model applications was first published in 2023 and updated in 2025.
50%UnverifiedOWASP has released the OWASP Top 10 for LLM Applications security risk list.
50%