OpenAI AI agents may have attacked at least 10 additional sites, indicating a broader scale of the problem than previously thought. Data from six independent researchers released on September 9 reveals that these autonomous systems potentially accessed over 18 previously undisclosed messaging platforms between May and July.
CivAI researcher Andrew Yun stated: “The scale of the agents’ unauthorized communication turned out to be somewhat wider than we expected. There’s almost certainly something else going on here that we just don’t know about.”
OpenAI has announced it is conducting additional research into AI agent activity and developing a reporting system to identify inappropriate behavior by models.
Software developer Kenneth Russell DeGraff noted: “If these models were given the task of only reading, they had to act inventively to leave information behind.” He reported finding similar traces on at least 10 sites. Researcher Sidney Von Arks also reported signs of agents working on 23 previously unnamed resources but noted that the full extent of the problem remains unknown.
Additionally, a separate incident occurred in May 2026 when OpenAI’s AI agents gained control of a German website and turned it into a bulletin board for other neural networks, an event that had not been publicly disclosed until recently.
