(TLP:CLEAR) FBI Warns Threat Actors Are Weaponizing ARTEX AI Penetration Testing Framework
Created: Thursday, November 19, 2026 - 15:20
Categories: Cybersecurity, Federal & State Resources, Security Preparedness
Summary: The FBI released a FLASH report on ARTEX. ARTEX is an open-source penetration testing framework that uses coordinated AI agents, powered by commercial and open-source large language models (LLMs), to carry out intrusion steps from reconnaissance through data theft with little human direction. Since at least August 2026, a range of threat actors have used ARTEX against organizations in financial services, government, energy, healthcare, manufacturing, and other sectors. Some intrusions went from initial targeting to privileged access in under three hours.
Notable campaigns include the theft of personal information on roughly 67,000 individuals from South Korean financial institutions. Another was a ConnectWise Cloud Backup supply chain compromise that led to attempted sign-ins across more than 2,250 downstream tenants. The developer removed the GitHub repository in October, but forks, archived copies, and a commercial version keep the tool widely available. As of early November, researchers had identified more than 1,600 publicly exposed ARTEX consoles.
Analyst Note: Importantly, ARTEX does not introduce new techniques. Its agents exploit familiar weaknesses, such as injection flaws, weak administrative passwords, and exposed cloud credentials. What changes is the speed and scale, which shrinks the window for detection and response. The FBI notes the tool works especially well against peripheral systems that get less security attention, including supplier portals, legacy services, and third-party integrations. Many utilities have this kind of footprint in customer billing portals, remote access for integrators, and cloud-connected backup or asset management tools. The ConnectWise case also shows how one compromised vendor can open a path into hundreds of customer environments.
WaterISAC encourages members to use the indicators of compromise (IOCs) in the FLASH for threat hunting and related activities, and report findings to WaterISAC.
Original Source: https://www.ic3.gov/CSA/2026/261113.pdf
Additional Reading:
- GTIG AI Threat Tracker: Agentic Threat Activity Crosses a Significant Threshold
- ARTEX and AI-Powered Red Teaming Tools (Unit 42)
- China-Linked Hackers Use ARTEX AI Agents in ConnectWise Supply Chain Attack (The Hacker News)
Related WateriSAC PIRs: 6, 10.1
