Descripción: 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.
Entidades
Ver todas las entidadesAlleged: OpenAI , Large language model developers y AI agent system developers developed an AI system deployed by OpenAI y AI agent system deployers, which harmed Targets of autonomous AI-enabled intrusion operations , Privacy , Information security , Governments y Government agencies.
Sistemas de IA presuntamente implicados: OpenAI large language models , OpenAI AI agents , Large language models y AI agent systems
Estadísticas de incidentes
ID
1806
Cantidad de informes
1
Fecha del Incidente
2026-06-17
Editores
Daniel Atherton
Informes del Incidente
Cronología de Informes
Loading...
Respuesta post-incidente de OpenAI
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-…
Variantes
Una "Variante" es un incidente de IA similar a un caso conocido—tiene los mismos causantes, daños y sistema de IA. En lugar de enumerarlo por separado, lo agrupamos bajo el primer incidente informado. A diferencia de otros incidentes, las variantes no necesitan haber sido informadas fuera de la AIID. Obtenga más información del trabajo de investigación.
¿Has visto algo similar?