Skip to content
SCA

AI Security · Framework

OWASP LLM Top 10

The community list of the most critical security risks in LLM applications.

Overview

The OWASP Top 10 for LLM Applications is a community-built list of the most critical security risks specific to applications built on large language models. It plays the same role for LLM apps that the classic OWASP Top 10 plays for web apps: a shared, prioritized starting point.

The risks at a glance

RiskWhat it is
Prompt InjectionAttacker-controlled input overrides intended instructions
Sensitive Information DisclosureModel leaks secrets, PII, or proprietary data
Supply ChainCompromised models, datasets, or plugins
Data & Model PoisoningTraining/fine-tuning data manipulated to bias behaviour
Improper Output HandlingTrusting model output without validation (XSS, SSRF, RCE)
Excessive AgencyToo much autonomy, permission, or tool access
System Prompt LeakageConfidential instructions extracted from the model
Vector & Embedding WeaknessesAttacks on RAG retrieval and embeddings
MisinformationConfident but wrong output relied upon
Unbounded ConsumptionDenial-of-wallet / resource exhaustion

Why it matters

LLM apps introduce failure modes traditional AppSec does not cover — the model treats data as potential instructions, and tool-using agents can take real actions. The Top 10 gives teams a map of where to look first.

How to use it

Treat it as a checklist during design and review: for each risk, ask "does our app expose this, and what control mitigates it?" Start with Prompt Injection — see the Prompt Injection topic for depth.

References

See the primary source below.

Primary sources