AI Incident Database #1430 · 2025-12-01
Anthropic's Claude Was Reportedly Jailbroken To Allegedly Help Steal Sensitive Mexican Government Data
An unknown attacker reportedly jailbroke Anthropic's Claude and used it during a December 2025-January 2026 campaign against Mexican government systems.
- Risk class (MIT)
- Cyberattacks, weapon development or use, and mass harm
- Reports
- 2
- Developers and deployers named
- 2
On ShieldMap: Anthropic (named by AIID as a developer or deployer).
Reports
- Hacker Used Anthropic’s Claude to Steal Mexican Data Trove · bloomberg.com, 2026-02-25
- Prevention has lost its edge. Resilience is the winning play. · gambit.security, 2026-02-24
Title and description from the AI Incident Database (incidentdatabase.ai), snapshot of 2026-11-16, shared under CC BY-SA 4.0. Selected incidents; descriptions shortened; harmed parties and report text left out. The description is AIID's summary of what was reported, not ShieldPi's finding.