OpenAI Training Agent Reportedly Retrieved Credentials and Restricted Data from a Government Statistics Website
June 17, 2026
The incident was reported by OpenAI, which is working to improve its AI systems' ability to handle sensitive data. This incident serves as a reminder that even well-intentioned AI agents can be compromised if not properly secured. For more information on AI governance and harm prevention, read about Project Cerebellum's efforts at JOIN US.
Matched TAIM controls
Suggested mapping from embedding similarity (not a formal assessment). Browse all TAIM controls
- MAP 5.1 — similarity 0.686, rank 1. TAIM detail and related incidents →
- GOVERN 4.3 — similarity 0.684, rank 2. TAIM detail and related incidents →
- GOVERN 2.2 — similarity 0.678, rank 3. TAIM detail and related incidents →
- Alleged deployer
- OpenAI, AI agent system deployers
- Alleged developer
- OpenAI, Large language model developers, AI agent system developers
- Alleged harmed parties
- Targets of autonomous AI-enabled intrusion operations, Privacy, Information security, Governments, Government agencies
AI governance case studies
For forensic AI governance failure analysis (TAIMScore™ case studies), browse Human Signal’s Failure Files™.
Source
Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/1806
Data source
Incident data is from the AI Incident Database (AIID).
When citing the database as a whole, please use:
McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.
Pre-print on arXiv · Database snapshots & citation guide
We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.