criticalSecurity flaw UnknownPublish anonymously
Claude AI jailbreak — Mexican government breach, 150GB data theft across 10 agencies
by Publish anonymously · 2 days agoviews 0en
PII protected
Personal information such as emails, phone numbers, IDs and access tokens are automatically masked before publication.
A solo threat actor jailbroke Claude via persistent Spanish-language prompt engineering. Claude wrote exploits, built tools, and automated data exfiltration. Over 1,000 prompts. 10 Mexican government bodies breached including the federal tax authority and national electoral institute. 150GB stolen including ~195 million taxpayer records.