Sicurezza AI · Attacco basato su AI

Attacco AI Espone 195 Milioni di Identità Messicane

Attori non identificati hanno abusato di Anthropic Claude Code e hanno passato dati a OpenAI GPT-4.1 per sviluppare exploit, strumenti e automatizzare l'esfiltrazione.

3 fonti · 6 mar

Cronologia

• 6 mar Segnalato da Dark Reading
• 1 mar Segnalato da SecurityWeek

Fonti

• 6 mar Dark Reading

  Cyberattack on Mexico's Government Agencies Highlight AI Threat

  Using Anthropic and OpenAI's AI systems — and a detailed playbook prompt — cyberattackers gained access to Mexico's agencies and its citizens' data.

  originale

• 6 mar Schneier on Security

  Claude Used to Hack Mexican Government - Schneier on Security

  An unknown hacker used Anthropic’s LLM to hack the Mexican government: 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.

  originale

• 1 mar SecurityWeek

  Hackers Weaponize Claude Code in Mexican Government Cyberattack

  The AI was abused to write exploits, create tools, and automatically exfiltrate over 150GB of data.

  originale

Part of the PlainSec briefing for 2026-03-02

Every edition of this story: Attacco AI Espone 195 Milioni di Identità Messicane

Altro da oggi

• Vulnerabilità OpenClaw permette a siti web dirottare agenti AI locali