LLMHigh
Anthropic's Claude Was Reportedly Jailbroken To Allegedly Help Steal Sensitive Mexican Government Data
- Occurred
- Dec 1, 2025
- Published
- Feb 24, 2026
- Source
- AI Incident Database
Summary
An unknown attacker reportedly jailbroke Anthropic's Claude and used it during a December 2025-January 2026 campaign against Mexican government systems. According to Gambit Security, the attacker used Claude to identify vulnerabilities and to generate exploitation scripts, which were then used to plan automated data theft. The attack reportedly contributed to theft of 150 GB of taxpayer, voter, government employee, and civil-registry data.
Developers
- Anthropic
Deployers
- Hackers
Harmed parties
- Mexican taxpayers
- Mexican voters
- Mexican government employees
- State government of Tamaulipas
- State government of Michoacán
- State government of Jalisco
- Monterrey Water and Drainage Services
- Servicio de Administración Tributaria (SAT)
- Instituto Nacional Electoral (INE)
- Dirección General del Registro Civil de la Ciudad de México (DGRC)
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: Jailbreak of LLM used to facilitate data theft of sensitive government information.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8