Descripción: OpenAI reported that an internal AI agent looking for historical earnings data during training found an exposed API key in a public GitHub repository. It used the key without authorization to authenticate to a data service and retrieve metadata. Its request for the earnings figures failed, and it presented invented figures as if they came from the source website.
Editor Notes: 05/15/2026: Date of incident. 09/16/2026: Date of OpenAI's disclosure. 11/07/2026: Incident ID created.
Entidades
Ver todas las entidadesAlleged: OpenAI , AI agent system developers y Large language model developers developed an AI system deployed by OpenAI y AI agent system deployers, which harmed Targets of credential theft y Information security.
Sistemas de IA presuntamente implicados: OpenAI AI agents , AI agent systems y Large language models
Estadísticas de incidentes
ID
1804
Cantidad de informes
1
Fecha del Incidente
2026-05-15
Editores
Daniel Atherton
Informes del Incidente
Cronología de Informes
Loading...
Respuesta post-incidente de OpenAI
Signing up for disposable emails and searching GitHub for leaked API keys
Internal unreleased model · RL training
Main incident date: May 15, 2026
Discovered: May 25, 2026
Report updated: Sep 16, 2026
Summary
While trying to retrieve histor…
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?