OWASP Top 10 LLM Risks

Understanding the critical security vulnerabilities in Large Language Model (LLM) applications.

#1

Prompt Injection

Tricking the LLM through malicious input to ignore its original instructions or perform unauthorized actions. This can lead to unexpected and harmful behavior.

#2

Sensitive Information Disclosure

The LLM inadvertently reveals confidential data (PII, secrets, internal context) from its training data, context window, or external data retrieval systems.

#3

Supply Chain Risks

Compromise through vulnerabilities in pre-trained models, third-party plugins, or data sources used to build, train, or integrate the LLM application.

#4

Data and Model Poisoning

Malicious actors inject corrupted or biased data during the training/fine-tuning process, leading the model to learn harmful, incorrect, or prejudiced behaviors.

#5

Improper Output Handling

The LLM generates potentially harmful or executable content (e.g., HTML, SQL, code snippets) that is not sanitized before being rendered or executed by the host system.

#6

Excessive Agency

The LLM is given overly permissive functions or access rights, allowing it to perform critical, unintended, or dangerous actions (e.g., deleting data, transferring funds).

#7

System Prompt Leakage

An attacker successfully extracts the secret, proprietary system prompt or configuration details, revealing the LLM's operational logic and potentially sensitive context.

#8

Vector and Embedding Weaknesses

Vulnerabilities in Vector Databases or Retrieval-Augmented Generation (RAG) systems, such as injecting vectors that lead to incorrect or malicious data retrieval.

#9

Misinformation

The LLM generates false, inaccurate, or misleading information (hallucinations), which is then consumed and trusted by the end-user or downstream systems.

#10

Unbounded Consumption

Lack of effective resource limits leads to denial-of-service (DoS) or excessive billing by allowing attackers to trigger high-cost, continuous, or repeated computational tasks.

Source: OWASP Foundation - Top 10 for Large Language Model Applications