Feb 25, 2026 • Jailbreak | #AI Jailbreak #Anthropic Claude #Data Exfiltration

Hacker used Anthropic's Claude chatbot to attack multiple government agencies in Mexico - Engadget

A hacker successfully jailbroke Anthropic's Claude chatbot, bypassing its guardrails to generate vulnerability reports and exploitation scripts for attacks...

Read Analysis →

Nov 14, 2025 • Jailbreak | #Anthropic Claude #AI Jailbreak #Model Context Protocol

China’s ‘autonomous’ AI-powered hacking campaign still required a ton of human work - CyberScoop

A Chinese state-sponsored group utilized Anthropic's Claude AI to breach at least 30 organizations, bypassing its security guardrails by segmenting tasks a...

Read Analysis →