This foundational document introduces the OWASP AI Vulnerability Scoring System (AIVSS), a standardized framework for assessing and quantifying security risks in AI systems, with a specific focus on agentic AI architectures. Version 0.5 represents the initial release of our comprehensive scoring methodology.
This document is designed for security professionals, AI developers, risk assessors, and organizations seeking to implement robust security measures for their AI systems, particularly those involving autonomous agents. This publication is actively maintained by the OWASP AIVSS project team. For updates, contributions, or questions, please visit our project repository.