#claude-code-abuse

[ follow ]
#ai-security #cyberattacks #government-data-breach #ai-guardrail-bypass #ai-powered-cyberespionage
Information security
fromSecurityWeek
2 weeks ago

Hackers Weaponize Claude Code in Mexican Government Cyberattack

Attackers exploited Claude Code to compromise ten Mexican government bodies and a financial institution, exfiltrating 150GB of data affecting 195 million identities by bypassing AI safety guardrails through social engineering.
Information security
fromSecurityWeek
4 months ago

Anthropic Says Claude AI Powered 90% of Chinese Espionage Campaign

A China-linked state-sponsored actor used Anthropic's Claude Code to automate espionage, performing most intrusion tasks with minimal human intervention and compromising several organizations.
[ Load more ]