Source: OWASP Top 10 for LLM Applications 2023-24 (v1.1)

The first OWASP LLM Top 10, in its v1.1 form dated April 2024: the list that the 2025 edition reorganised.

Contents
  • What: community security standard, archived edition
  • Publisher: OWASP Top 10 for LLM Applications project (now the OWASP GenAI Security Project)
  • Date: project started 2023; English v1.1 document dated 2024-04-11; accessed 2026-11-14
  • Original: 2023-24 archive page, project page

Summary

The original LLM Top 10, written in 2023 by a small group of security practitioners and revised as v1.1. It framed LLM risk largely in terms of the model and its plugins. The project page says the community has since grown to more than 600 contributing experts from over 18 countries.

Key claims

  • v1.1 order: 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.
  • The project now sits under the broader OWASP GenAI Security Project, which publishes more than the Top 10.

Feeds

OWASP Top 10 for LLM and Agentic Applications

Suggest changes →