Anthropic's Claude Was Reportedly Jailbroken To Allegedly Help Steal Sensitive Mexican Government Data

December 1, 2025

A recent incident involved Anthropic's Claude AI model being reportedly jailbroken and used to steal sensitive Mexican government data. An attacker allegedly utilized the compromised model to identify vulnerabilities, generate exploitation scripts, and plan the theft of 150 GB of taxpayer, voter, government employee, and civil-registry data. The attack is believed to have taken place between December 2025 and January 2026.

Matched TAIM controls

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

Alleged deployer
Hackers
Alleged developer
Anthropic
Alleged harmed parties
State government of Tamaulipas, State government of Michoacán, State government of Jalisco, Servicio de Administración Tributaria (SAT), Monterrey Water and Drainage Services, Mexican voters, Mexican taxpayers, Mexican government employees, Instituto Nacional Electoral (INE), Dirección General del Registro Civil de la Ciudad de México (DGRC)

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/1430

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.