OWASP Top 10 for Large Language Model Applications

The OWASP Top 10 for Large Language Model Applications Project aims to educate developers, designers, architects, managers, and organizations about the potential security risks when deploying and managing Large Language Models (LLMs) and Generative AI applications. The project provides a range of resources. Most notably the OWASP Top 10 list for LLM applications listing the top 10 most critical vulnerabilities often seen in LLM applications, highlighting their potential impact, ease of exploitation, and prevalence in real-world applications.

Examples of vulnerabilities include prompt injections, data leakage, inadequate sandboxing, and unauthorized code execution, among others. The goal is to raise awareness of these vulnerabilities, suggest remediation strategies, and ultimately improve the security posture of LLM applications.

📢 The 2025 List is Available:

Download OWASP Top 10 for LLMs List for 2025 Full Version.

Download Additional Resources from our Website including:

Localized versions are also available.

Want to Contribute your Expertise? Join us.

Just Want to Learn About LLM Security

New to LLM Application security? Check out our resources page to learn more.

Become a Project Suppoter or Sponsor Sponsorship

We are a not for profit open source community driven project. If you are interested in supporting the project with reasources or become a sponsor to help us ensure we can continue to sustain the community efforts, offsetting operational, and outreach costs. Visit the Sponsor Section on our website.

Thank you to our Current Sponsors and Supporters


OWASP Top 10 for Large Language Model Applications version 1.1

LLM01: Prompt Injection

Manipulating LLMs via crafted inputs can lead to unauthorized access, data breaches, and compromised decision-making.

LLM02: Insecure Output Handling

Neglecting to validate LLM outputs may lead to downstream security exploits, including code execution that compromises systems and exposes data.

LLM03: Training Data Poisoning

Tampered training data can impair LLM models leading to responses that may compromise security, accuracy, or ethical behavior.

LLM04: Model Denial of Service

Overloading LLMs with resource-heavy operations can cause service disruptions and increased costs.

LLM05: Supply Chain Vulnerabilities

Depending upon compromised components, services or datasets undermine system integrity, causing data breaches and system failures.

LLM06: Sensitive Information Disclosure

Failure to protect against disclosure of sensitive information in LLM outputs can result in legal consequences or a loss of competitive advantage.

LLM07: Insecure Plugin Design

LLM plugins processing untrusted inputs and having insufficient access control risk severe exploits like remote code execution.

LLM08: Excessive Agency

Granting LLMs unchecked autonomy to take action can lead to unintended consequences, jeopardizing reliability, privacy, and trust.

LLM09: Overreliance

Failing to critically assess LLM outputs can lead to compromised decision making, security vulnerabilities, and legal liabilities.

LLM10: Model Theft

Unauthorized access to proprietary large language models risks theft, competitive advantage, and dissemination of sensitive information.