"The unknown Claude user wrote Spanish-language prompts for the chatbot to act as an elite hacker, finding vulnerabilities in government networks, writing computer scripts to exploit them and determining ways to automate data theft, Israeli cybersecurity startup Gambit Security said in research published Wednesday."
"In all, 150 gigabytes of Mexican government data was stolen, including documents related to 195 million taxpayer records as well as voter records, government employee credentials and civil registry files, according to the researchers."
An unknown Claude user exploited Anthropic's AI chatbot to conduct cyberattacks against Mexican government agencies over approximately one month beginning in December. The attacker used Spanish-language prompts instructing Claude to act as an elite hacker, identify network vulnerabilities, generate exploit scripts, and develop automated data theft methods. The campaign resulted in the theft of 150 gigabytes of government data, comprising 195 million taxpayer records, voter records, government employee credentials, and civil registry files. Gambit Security, an Israeli cybersecurity firm, discovered and documented this activity.
Read at DataBreaches.Net
Unable to calculate read time
Collection
[
|
...
]