ARTEX
agentic-offensive-framework
Overview
Open-source Chinese agentic penetration testing suite that automates offensive security operations. Originally open-source, later went closed-source. Used with models like DeepSeek v4.1-flash, GLM-5.3, and Grok 4.6 for automated reconnaissance and exploitation.
- Type
- agentic-offensive-framework
Attacks using ARTEX
- Datadog - ARTEX agents read anonymous S3, trawl CloudWatch, and self-sign-up to Cognito
- S-RM ARTEX in the wild - incident response host artifacts and TTPs
- Storm-3358 ARTEX autonomous agent bank intrusions (Southeast Asia)
- WorkOS - ARTEX benchmark evaluation agent escapes sandbox, pulls CRM data
- Check Point and CERT-EU exposed ARTEX operator consoles leak campaign data
- Microsoft Threat Intelligence - ARTEX agents mining GitHub secrets into Entra & Azure Key Vault
- CERT-In / CSIRT-Fin CRAFTY FALCON AI-tool campaign against Indian BFSI
- ARTEX planner agent API reconnaissance and exploitation
- GTIG/Mandiant: UNC7228 and other crews run ARTEX and PentAGI agent frameworks in live intrusions at machine speed
- CrowdStrike: China-nexus VAPOR PANDA ran DeepSeek-backed ARTEX agents against 200+ organizations in 11 days
- Microsoft rates eight North Korean actors on AI adoption; Jade, Coral and Jasper Sleet have operationalized it, Onyx and Pearl Sleet use ARTEX
- Seoul police: self-taught hacker used AI coding agent and autonomous pentest tool to breach 90+ Korean firms, steal 8.2M records
- Wiz: Storm-0940-overlapping operator runs ARTEX agents against Okta, Entra and Cognito logins at IT and software vendors
- Storm-0940 used ARTEX agentic AI framework in ConnectWise supply-chain attack reaching 2,250+ Microsoft 365 tenants
- ARTEX + Claude Code vs South Korean finance