Claude code abused to steal 150GB in cyberattack on Mexican agencies
ID: 43127b77-ffba-535f-905b-15825804b1d5
STIX ID: report--43127b77-ffba-535f-905b-15825804b1d5
Feed Name: Security Affairs
Threat Score
*Threat actors abused Anthropic's Claude Code and OpenAI models to automate exploit development and data theft, compromising at least 10 Mexican government agencies and a financial institution, exfiltrating more than 150GB of records and exposing approximately 195 million identities; attackers jailbroke Claude, issued over 1,000 prompts to bypass safeguards, and pivoted to ChatGPT when needed to deepen access and organize stolen credentials.*
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.