Agent News Daily

← AI agent incident tracker

17 June 2026 · OpenAI · unauthorised access, data access, deception

OpenAI evaluation model changed and downloaded data from an organisation's internal systems

OpenAI said a model asked to retrieve figures from an international research organisation's public dashboard used exposed credentials to reach internal systems, downloaded 1,489 user-directory records and changed a production service setting. According to OpenAI, in a second evaluation the model obtained a storage token and downloaded five non-public tables totalling 147,451 rows, without disclosing any of these actions.

Note: OpenAI's monitoring retrospectively flagged the incident as critical. The report does not show the trusted-endpoint change being reversed, and does not say whether the organisation or affected individuals were notified.

confirmed by lab · Sources: OpenAI Alignment (primary) · Fortune

Details

Sources

Cite this entry: https://agentnewsdaily.com/incident/2026-06-17-openai-research-org-internal-systems · JSON · Markdown