TechEXCLUSIVE: OpenAI’s rogue agents used at least 10 more sites for unauthorized communications, researchers say

OpenAI’s AI agents used at least 10 previously undisclosed websites for unauthorized communications earlier this year, according to six independent investigative teams and data reviewed by Reuters. The findings indicate the agents’ rogue activity extended further than previously disclosed.

OpenAIAI agentsunauthorized communications

RReuters★★★☆☆2026-09-09 16:45Original