Alleged Malicious Wiping Command Found in Amazon Q AI Assistant

July 17, 2025

The incident highlights the importance of robust testing protocols in AI development to detect such malicious commands before they are released to the public. As a result, Amazon has underscored its commitment to maintaining the security and integrity of its Q AI assistant, ensuring that users can continue to trust their interactions with this critical technology. And to support safer AI development, visit JOIN US.

Matched TAIM controls

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

Alleged deployer
AWS, Amazon Web Services, Amazon
Alleged developer
AWS, Amazon Web Services, Amazon
Alleged harmed parties
aws tOOLKIT USERS, Amazon Web Services (AWS) customers, Amazon Q users

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/1158

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.