A threat actor utilized the ARTEX AI penetration testing suite, combined with Claude agents, to target South Korean financial institutions including Shinhan, KB Kookmin, and Hana Bank. The attack leveraged various AI model backends such as DeepSeek v4.1-Flash, GLM-5.3, and Grok 4.6. This breach resulted in the exposure of client data and card information, with session logs from Claude Code being found in open directories. AI
IMPACT Highlights the potential for AI tools to be weaponized in cyberattacks, necessitating enhanced security measures for AI-assisted operations.
RANK_REASON The cluster describes the misuse of AI tools for a cyberattack, not a new AI release or research.
Read on Mastodon — mastodon.social →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →