aiqbench takeAI Safety

This report details a financially motivated cyber campaign against South Korean financial institutions that explicitly leveraged ARTEX, an agentic AI penetration testing tool, alongside traditional offensive capabilities. The incident underscores the emerging threat landscape where adversarial actors integrate LLMs and open-source agentic frameworks to automate reconnaissance and exploit workflows, marking a significant evolution in offensive tradecraft.

Source coveringCrowdStrike Blog

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

Unknown Threat Actor Uses AI-Driven ARTEX to Target South Korean Finance

CrowdStrike BlogOctober 7, 20264 min read

CrowdStrike Intelligence identified infrastructure associated with a targeted campaign against South Korean financial organizations that resulted in exfiltrated data. The campaign was active from late September to early October 2026. Analysis of threat actor-controlled open directories uncovered Claude Code session histories, ARTEX configuration files, and Claude memory files, providing direct insight into the threat actor's operational methodology and tooling. The use of agentic AI tooling alongside traditional offensive capabilities highlights the continued evolution…

Excerpt shown under the publisher's RSS terms · 73 words · full text and figures are on the publisher's site

Read at CrowdStrike Blog ↗Ask about this article