INSPECTING ARCHIVED INTELLIGENCE (OUTDATED VERSION).

ARTEX AI Tool Used to Steal Data from South Korean

| 2026-10-08 14:12 CRITICAL HIGH AI-ENABLED ATTACK · AUTONOMOUS DATA BREACH
Executive Summary
AI-generated
A recent attack against South Korean financial organizations, which began in late September and ended with stolen data, utilized the open-source AI tool ARTEX from China. The attacker is believed to be Chinese-speaking and financially motivated, based on the use of the tool and Chinese-language prompts. The affected institutions are not specified by number, but industry reports describe several South Korean financial organizations breached during this period. The attack involved combining ARTEX with large language models (LLMs) to conduct penetration tests, as revealed through open directories left behind by the attacker on servers controlled by them. These directories exposed session histories, configuration files, and memory files, providing insight into the threat actor's operational methodology and tooling.
Technical Mitigations AI-generated
• Reset credentials and API keys that may have been exposed, and review access logs for the affected accounts or integrations.
Technical Observables 12 IoCs Login Required
Indicators of Compromise (IoCs) Protected

Raw threat telemetry, malicious IP addresses, file hashes, and direct VirusTotal correlation are restricted to authenticated users.

urls 1 domains 1 ips 10
Intelligence Metadata
Actors / Malware / CVEs / Campaigns
ARTEXARTEX
Target & Sectors
CN KR
financefinance
Incident Timeline
‎2026/10/08
A Chinese-speaking, financially motivated threat actor used the recently released open-source AI pen testing tool ARTEX to breach several South Korean financial organizations and steal customer and employee data between late September and early October 2026.
organisation ARTEX
organisation Telegram
organisation NFT
organisation CrowdStrike
organisation IP
organisation LLM
organisation AI-Driven
organisation HTML
organisation SpaceXAI
organisation Google Gemini
organisation Google
organisation WebGL
organisation Zhipu AI
organisation SecurityAffairs
organisation SCARLET LOOP Uses AI for Account Takeover
organisation Target
organisation OpenAI
organisation The Hacker News
data_breach 12,277,358 credentials
data_breach 11,832 credentials
infrastructure 3,968 domains
organisation Cyber Security News
Tactical Metrics
Metrics
data_breach
12,277,358
Credentials
Metrics
data_breach
11,832
Credentials
Metrics
infrastructure
3,968
Domains