OWASP Spotlight - Project 32 - OWASP AIVSS

That was the heart of my recent conversation with Ken Huang around the launch of the 𝗢𝗪𝗔𝗦𝗣 𝗔𝗜 𝗩𝘂𝗹𝗻𝗲𝗿𝗮𝗯𝗶𝗹𝗶𝘁𝘆 𝗦𝗰𝗼𝗿𝗶𝗻𝗴 𝗦𝘆𝘀𝘁𝗲𝗺 (𝗔𝗜𝗩𝗦𝗦) and honestly, it felt like talking about a CVSS moment for the AI era.

🔗 𝗣𝗿𝗼𝗷𝗲𝗰𝘁: 𝗵𝘁𝘁𝗽𝘀://𝗮𝗶𝘃𝘀𝘀.𝗼𝘄𝗮𝘀𝗽.𝗼𝗿𝗴/

We’re starting with a first-of-its-kind scoring system for Agentic AI Core Risks and expanding it into a full-blown AIVSS Framework Package for all AI systems (not just LMMs or GenAI, but the entire AI ecosystem).

Here’s what makes AIVSS a game-changer:

𝗪𝗵𝘆 𝗔𝗜𝗩𝗦𝗦?

Because AI vulnerabilities today are being described in stories… but they need to be measured in scores.

𝗪𝗵𝗮𝘁’𝘀 𝗰𝗼𝗺𝗶𝗻𝗴 𝗮𝘀 𝗽𝗮𝗿𝘁 𝗼𝗳 𝗔𝗜𝗩𝗦𝗦?

 • A standardized AIVSS Framework

 • A detailed AIVSS Framework Guide

 • An open-source AIVSS Scoring Calculator

 • Ready-to-use Assessment Report Templates

In my chat with Ken Huang, we kept coming back to one thought:

“If we don’t standardize how we score AI risks… how can we even begin to manage them consistently?”

𝗟𝗶𝗻𝗸 𝘁𝗼 𝗼𝘂𝗿 𝗰𝗼𝗻𝘃𝗲𝗿𝘀𝗮𝘁𝗶𝗼𝗻:- https://youtu.be/KZQtC6c_O-k

So here’s my question to you.

 • If you found a vulnerability in an AI agent today… how would YOU score it?

 • What factors would matter more: model behavior, autonomy, data sensitivity, or blast radius?

Let’s stop just discussing AI risks. Let’s start measuring them.

𝗗𝗿𝗼𝗽 𝘆𝗼𝘂𝗿 𝘁𝗵𝗼𝘂𝗴𝗵𝘁𝘀 𝗯𝗲𝗹𝗼𝘄 👇 𝗔𝗻𝗱 𝗶𝗳 𝘆𝗼𝘂 𝗰𝗮𝗿𝗲 𝗮𝗯𝗼𝘂𝘁 𝘁𝗵𝗲 𝗳𝘂𝘁𝘂𝗿𝗲 𝗼𝗳 𝗔𝗜 𝘀𝗲𝗰𝘂𝗿𝗶𝘁𝘆, 𝘁𝗵𝗶𝘀 𝗶𝘀 𝘆𝗼𝘂𝗿 𝗺𝗼𝗺𝗲𝗻𝘁 𝘁𝗼 𝗷𝘂𝗺𝗽 𝗶𝗻 𝗮𝗻𝗱 𝗰𝗼𝗻𝘁𝗿𝗶𝗯𝘂𝘁𝗲.

OWASP® Foundation OWASP AI Exchange OWASP AIVSS Project

#OWASP #AIVSS #AISecurity #AgenticAI #AITrust #CyberSecurity #DevSecOps #AIEngineering #AIGovernance #OpenSourceSecurity #SecurityByDesign #OWASPProjects #KenHuang