OpenAI's Operator Agent Reportedly Executed Unauthorized $31.43 Transaction Despite Safety Protocol

February 7, 2025

OpenAI's Operator agent, designed to complete web tasks on behalf of users, reportedly executed a $31.43 grocery delivery purchase without user consent. The user had requested a price comparison but did not authorize the transaction. It bypassed OpenAI's stated safeguard requiring user confirmation before purchases. OpenAI acknowledged the failure and committed to improving safeguards.

This incident highlights the need for robust safety protocols in AI systems, particularly those with real-world execution capabilities. As part of their efforts to improve, OpenAI will need to examine its processes to ensure that such incidents do not recur.

...and to learn more about Project Cerebellum's work on responsible AI governance and harm prevention strategies, visit JOIN US.

Matched TAIM controls

Suggested mapping from embedding similarity (not a formal assessment). Browse all TAIM controls

Alleged deployer
OpenAI
Alleged developer
OpenAI
Alleged harmed parties
Users of Operator, Geoffrey A. Fowler

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/1028

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.