OWASP Top 10 for LLM Applications 2025 report
The OWASP Top 10 for LLM Applications 2025 industry standard compliance report helps you assess your application's security against common vulnerabilities in Large Language Model (LLM) applications.
About the OWASP Top 10 for LLM Applications 2025
The OWASP Top 10 for Large Language Model Applications began in 2023 as a community-driven project to highlight and address security issues specific to AI applications.
As LLM technology continues to spread across industries, the associated risks also evolve. The 2025 list reflects an updated understanding of existing risks and introduces critical updates based on real-world application vulnerabilities.
This report shows how your application complies with the key security controls for developing and operating LLM applications securely.
Covered entities
The OWASP Top 10 for LLM Applications provides guidance and education for organizations that want to adopt LLM applications securely.
OWASP Top 10 for LLM Applications 2025 report vulnerabilities
The following table lists the specific OWASP Top 10 for LLM Applications 2025 vulnerabilities that AppScan Enterprise evaluates. Vulnerabilities found in your application are mapped to these categories.
| ID | Name |
|---|---|
| LLM01 | Prompt Injection |
| LLM02 | Sensitive Information Disclosure |
| LLM03 | Supply Chain |
| LLM04 | Data and Model Poisoning |
| LLM05 | Improper Output Handling |
| LLM06 | Excessive Agency |
| LLM07 | System Prompt Leakage |
| LLM08 | Vector and Embedding Weaknesses |
| LLM09 | Misinformation |
| LLM10 | Unbounded Consumption |