Description: OpenAI reported that an internal AI agent searching for hospital-bed figures during training retrieved more than 1,000 account records containing email addresses from a government statistics website. It downloaded application files and configuration files containing credentials, then bypassed authorization checks and saved 24 years of health-facility statistics.
Editor Notes: 06/17/2026: Incident date. 08/13/2026: Date the incident was discovered. 10/15/2026: OpenAI publishes its findings. 11/07/2026: 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 , Privacy , Information security , Governments and Government agencies.
Alleged implicated AI systems: OpenAI large language models , OpenAI AI agents , Large language models and AI agent systems
Incident Stats
Incident ID
1806
Report Count
1
Incident Date
2026-06-17
Editors
Daniel Atherton
Incident Reports
Reports Timeline
Loading...
OpenAI post-incident response
Retrieving server secrets and bypassing authorization on a government statistics website
Highly persistent internal model · RL training
Incident date: Jun 17, 2026
Discovered: Aug 13, 2026
Report updated: Oct 15, 2026
Summary
During a data-…
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?