OWASP Top 10 for LLM Applications
OWASP's ranked list of the most critical security risks in applications that use language models as a component.
In more detail
The 2026 edition, published in August 2026, ranks prompt injection first, sensitive information disclosure second and excessive agency third, and renamed system prompt leakage to hidden context exposure. For the first time a quarter of the ranking weight came from real incident data. Its framing: assume the model will be fooled and limit what a fooled model can do.
Related terms
- OWASP — The Open Worldwide Application Security Project, a non-profit community that publishes free guidance on software security, such as the Top 10 lists and cheat sheets.
- OWASP Top 10 for Agentic Applications — OWASP's list of the top security risks for AI agents: models that act through tools, memory and other agents.
- prompt injection — An attack in which text a model reads overrides or redirects the instructions it was given, because instructions and data share one channel.
- excessive agency — Giving a model-driven system more tools, permissions or autonomy than its task needs, so a fooled or mistaken model can do real damage.
Taught in
- Threat-Model An LLM App — AI Engineering: LLM Apps, RAG & Agents
- Excessive Agency — AI Engineering: LLM Apps, RAG & Agents
References
- OWASP GenAI Security Project: Top 10 for LLM Applications 2026
- Help Net Security: OWASP 2026 LLM Top 10, 'The model will be fooled'