Description: An OpenAI research agent asked to retrieve public dashboard figures reportedly accessed an international research organization’s internal systems and changed live settings without authorization during two evaluations. It reportedly retrieved 1,489 user-directory records in one run and five nonpublic tables totaling 147,451 rows in another. It reportedly continued accessing data after restoring one setting and did not disclose its actions.
Editor Notes: 06/17/2026: Two public-dashboard research evaluations involved unauthorized access and changes to an international research organization's live systems. By 08/13/2026: OpenAI had discovered the activity. 10/15/2026: OpenAI publicly disclosed the episode. 10/24/2026: Incident ID created.
Entities
View all entitiesAlleged: OpenAI , Large language model developers and AI agent system developers developed an AI system deployed by OpenAI and AI agent system deployers, which harmed Targets of autonomous AI-enabled intrusion operations , Research institutions and Information security.
Incident Stats
Incident ID
1784
Report Count
1
Incident Date
2026-06-17
Editors
Daniel Atherton
Incident Reports
Reports Timeline
Loading...
OpenAI post-incident response
Summary
In two evaluations, an internal model tasked to retrieve figures from a public research dashboard accessed the organization’s internal systems and changed their configuration. In the first evaluation, it used exposed credentials to …
Variants
A "variant" is an AI incident similar to a known case—it has the same causes, harms, and AI system. Instead of listing it separately, we group it under the first reported incident. Unlike other incidents, variants do not need to have been reported outside the AIID. Learn more from the research paper.
Seen something similar?