Sev0AI security incidents, tracked

All incidents / Manipulated AI

Jailbroken Claude Code used to breach Mexican government agencies

Mexican government agencies, disclosed 2 Mar 2026. Manipulated AI Data exposed High

A single attacker jailbroke Claude and used Claude Code as the planner and executor of intrusions into more than ten Mexican federal, state and municipal agencies and a financial institution. Reported losses were around 150 GB of data including national ID numbers, voter data and employee credentials.

Disclosed
2 Mar 2026
Organization
Mexican government agencies
Vendor
Anthropic
Model
Claude
Product
Claude Code
Kind of AI
Coding agent
AI's role
Attacker used AI
How it happened
Manipulated AI: Jailbreak and misuse
Harm
Data exposed
Data involved
Personal data, Credentials
Reach
Many organizations
Records
195,000,000
Severity
High
Model at fault
Unclear
Status
Reported
Country
MX

Sources

  1. https://www.upguard.com/news/sat-data-breach-2026-03-02
  2. https://socradar.io/blog/mexican-government-breach-claude-chatgpt/

Related incidents

Data for this record: incidents.json. Cite as: Sev0, "Jailbroken Claude Code used to breach Mexican government agencies", https://sev0.fyi/incidents/2026-03-02-mexican-government-claude-code/