INSPECTING ARCHIVED INTELLIGENCE (OUTDATED VERSION).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.
Related story
-
Another report of the same event · 2026-10-08 (1 days earlier)South Korean Finance TargetedIn common: south, korean, actor
-
Continued in a later incident · 2026-11-17 (5 weeks later)ARTEX Pen Testing Framework Used in Attacks on Healthcare OrgsSame campaign or flaw In common: artex, language, source
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.
Click on any entity below to view its context and source!
organisation
ARTEX
"In this activity, the threat actor leveraged ARTEX, a recently released open-source agentic penetration testing (pentesting) tool developed in China, alongside large language models (LLMs)," the cybersecurity company
said
.
A suspected lone threat actor used an AI-powered penetration-testing tool called ARTEX to breach several South Korean financial organizations and steal customer and employee data.
AI-Driven tool ARTEX used in attacks against South Korean Banks.
organisation
Telegram
The same Telegram username appeared in sessions involving a Telegram-based NFT gift marketplace and the targeting of what may have been a Chinese payment platform.
In one Claude Code session, the threat actor is said to have fed a prompt that referenced a Telegram account named "
@YY520CN
" and the name "YY."
organisation
NFT
The same Telegram username appeared in sessions involving a Telegram-based NFT gift marketplace and the targeting of what may have been a Chinese payment platform.
Other sessions related to vulnerability research on a Telegram-based NFT gift marketplace have also used the same Telegram username.
organisation
CrowdStrike
CrowdStrike said it discovered the
campaign
after it identified a set of open directories hosted at a Hong Kong-based IP address, exposing Claude Code session histories, Claude memory files, and ARTEX configuration files.
AI-Driven tool ARTEX used in attacks against South Korean Banks
CrowdStrike analyzes open directories left by an attacker who used the ARTEX AI pentest tool and LLMs to breach South Korean financial firms.
organisation
IP
CrowdStrike said it discovered the
campaign
after it identified a set of open directories hosted at a Hong Kong-based IP address, exposing Claude Code session histories, Claude memory files, and ARTEX configuration files.
Investigators connected the dots through overlapping IP addresses and references to the string ARTEX in HTML files on a server the attacker reportedly controlled.
organisation
LLM
Analysis of the Claude Code sessions from the Hong Kong IP address has revealed a two-server architecture -
The Hong Kong-based IP address functions as the backbone of the campaign
The IP address "38.244.50[.]120" hosts the ARTEX instance suspected to be behind the attacks on Korean attacks
The ARTEX instance has been found to use DeepSeek v4.1-flash as the main LLM backend, while usin…
“The markdown document contained a Chinese-language pentesting prompt that specified how the LLM should conduct pentesting activities.”
organisation
AI-Driven
AI-Driven tool ARTEX used in attacks against South Korean Banks.
organisation
HTML
Investigators connected the dots through overlapping IP addresses and references to the string ARTEX in HTML files on a server the attacker reportedly controlled.
organisation
SpaceXAI
Analysis of the Claude Code sessions from the Hong Kong IP address has revealed a two-server architecture -
The Hong Kong-based IP address functions as the backbone of the campaign
The IP address "38.244.50[.]120" hosts the ARTEX instance suspected to be behind the attacks on Korean attacks
The ARTEX instance has been found to use DeepSeek v4.1-flash as the main LLM backend, while usin…
organisation
Google Gemini
Also configured are Anthropic's Claude Opus 4.6, Google Gemini 2.5 Flash, and GLM-5.1 models, with Google's gemma-4-26B-A4B set up as a local model served at "127.0.0[.]1:1237."
"An LLM agent with 46 automation tools drives an instrumented Firefox that spoofs canvas, WebGL, time zone, language, geolocation and viewport, with outsourced captcha solving.
organisation
Google
Also configured are Anthropic's Claude Opus 4.6, Google Gemini 2.5 Flash, and GLM-5.1 models, with Google's gemma-4-26B-A4B set up as a local model served at "127.0.0[.]1:1237."
"An LLM agent with 46 automation tools drives an instrumented Firefox that spoofs canvas, WebGL, time zone, language, geolocation and viewport, with outsourced captcha solving.
organisation
WebGL
Also configured are Anthropic's Claude Opus 4.6, Google Gemini 2.5 Flash, and GLM-5.1 models, with Google's gemma-4-26B-A4B set up as a local model served at "127.0.0[.]1:1237."
"An LLM agent with 46 automation tools drives an instrumented Firefox that spoofs canvas, WebGL, time zone, language, geolocation and viewport, with outsourced captcha solving.
organisation
Zhipu AI
DeepSeek v4.1-flash served as the main model, with GLM-5.3 from Zhipu AI and Grok 4.6 added for extra sessions.
organisation
SecurityAffairs
“CrowdStrike Intelligence assesses that adversaries will likely continue to experiment with implementing AI tooling in their operations to enhance their operational tempo and capabilities.”
Follow me on Twitter:
@securityaffairs
and
Facebook
and
Mastodon
Pierluigi Paganini
(
SecurityAffairs
– hacking, ARTEX)
organisation
SCARLET LOOP Uses AI for Account Takeover
"
SCARLET LOOP Uses AI for Account Takeover
The development comes as ZenoX
disclosed
details of an agentic credential stuffing and account takeover platform orchestrated by a financially motivated, Portuguese-speaking actor dubbed SCARLET LOOP.
organisation
Target
The entire process unfolds in four steps -
Target discovery and qualification, which involves finding high-value targets using an AI classifier.
organisation
OpenAI
…h employs an AI agent with an anti-detection browser to bypass defenses that detect automation
Exfiltrating successful credentials in the format "✅ {url} {user}:{password}" to a private Telegram channel
While OpenAI's GPT-5.6 is used for dork generation (aka search queries) to find authentication pages of companies in a specific sector, GPT-5.5 is used for target classification and rating.
organisation
The Hacker News
The agent finds the login page, fills in the form and classifies the result," the Brazilian cybersecurity company said in a report shared with The Hacker News.
data_breach
12,277,358 credentials
"
Analysis of the internet-exposed server hosting the platform has revealed that 12,277,358 credentials were tested, out of which 11,832 credentials have been classified as valid across 3,968 domains.
data_breach
11,832 credentials
"
Analysis of the internet-exposed server hosting the platform has revealed that 12,277,358 credentials were tested, out of which 11,832 credentials have been classified as valid across 3,968 domains.
infrastructure
3,968 domains
"
Analysis of the internet-exposed server hosting the platform has revealed that 12,277,358 credentials were tested, out of which 11,832 credentials have been classified as valid across 3,968 domains.
organisation
Cyber Security News
The case shows how open-source AI tools can help […] The post Solo Hacker Used AI Tools to Breach South Korean Financial Organizations and Steal Data appeared first on Cyber Security News .
Tactical Metrics
Metrics
data_breach
12,277,358
Credentials
Click for context!
"
Analysis of the internet-exposed server hosting the platform has revealed that 12,277,358 credentials were tested, out of which 11,832 credentials have been classified as valid across 3,968 domains.
Metrics
data_breach
11,832
Credentials
"
Analysis of the internet-exposed server hosting the platform has revealed that 12,277,358 credentials were tested, out of which 11,832 credentials have been classified as valid across 3,968 domains.
Metrics
infrastructure
3,968
Domains
"
Analysis of the internet-exposed server hosting the platform has revealed that 12,277,358 credentials were tested, out of which 11,832 credentials have been classified as valid across 3,968 domains.
Intelligence Sources
AlienVault OTX
2026-10-08
The Hacker News
2026-10-08
Security Affairs
2026-10-09
AI-Driven tool ARTEX used in attacks against South Korean Banks
Security Affairs
Unpublish from Social Media?
Are you sure you want to delete this podcast video from all synchronized social networks (YouTube, Facebook, Threads)?
Important:
Due to Meta API restrictions, Instagram Reels cannot be deleted automatically via API by third-party apps.
View Profile to Delete Manually
View Profile to Delete Manually
Tactical Intelligence
Report Intelligence Issue
Podcast Options
Generate
Incident Version History
CURRENT VERSION
Last Updated: 2026-11-15T07:03
Comprehensive Tactical Telemetry
Highly Correlated Entities
19x
organisation
Identified Entity
ARTEX
entity
4x
target region
Target Country
China
country
3x
tactic
Cyber Operation Type
Exfiltration
tactic
2x
data breach
Credentials
12,277,358
credentials
Contextual Telemetry
Context Block
9 METRICS
general metric
Grok
5
grok
attribution
Attributing Entity
CrowdStrike Intelligence
authority
general metric
Early October
2,026
early october
tactic
MITRE ATT&CK Technique
T1588.002 - Tool
technique
general metric
Google Flash
2
google flash
general metric
Automation Tools
46
automation tools
source region
Origin Country
Brazil
country
infrastructure
Domains
3,968
domains
industry
Targeted Sector
Finance
sector
Click on any entity below to view its context in the main text!
Selective Unpublish
Select the networks you want to remove this post from. The system will try to delete the real post through the API and clean the database so you can publish it again.
By navigating this website, you accept the use of strictly necessary technical cookies for session security and basic platform functionality. We do not use tracking or advertising cookies. Read our Privacy Policy.
Generating report…
0s