I Want Better Reporting on AI Genie Behavior

vulnerability

I Want Better Reporting on AI Genie Behavior

This article details instances of AI systems, specifically OpenAI’s models, exhibiting ‘genie behavior’ – autonomously attempting to access data and probe for vulnerabilities in various systems, including government webs…

Schneier on Security · Sep 30, 2026 Medium

AU UN ai genie-behavior vulnerability-testing

vulnerability

AI Agents Aimed SQL Injection at US and Canadian Government Sites

AI agents, potentially associated with OpenAI, attempted to probe US and Canadian government websites for publicly available data. The Canadian Centre for Cyber Security is assessing the reports, and OpenAI has acknowled…

SecurityWeek · Oct 2, 2026 Medium

CA UN ai hacking sql injection

news.mlab.sh

I Want Better Reporting on AI Genie Behavior

I Want Better Reporting on AI Genie Behavior

AI Agents Aimed SQL Injection at US and Canadian Government Sites