The Federal Bureau of Investigation released FLASH-20261113-001 on 13 November 2026, a TLP:CLEAR alert warning that malicious actors have used the ARTEX autonomous penetration testing framework since at least August 2026 to compromise organizations worldwide. Some intrusions went from initial targeting to privileged access in under three hours.
Quick Take
- What: ARTEX is a multi-agent penetration testing framework written in Go that turns plain-language goals into machine commands with little human involvement after the objective is set.
- Who is affected: Organizations running internet-exposed applications, self-service portals, cloud infrastructure and partner or supplier systems across financial services, government, technology, defense, semiconductor, energy, healthcare, manufacturing, telecommunications and legal sectors.
- Speed: Some intrusions went from initial targeting to privileged access in under three hours.
- Models used: Chinese models are most prevalent on attacker-controlled instances, led by the DeepSeek Flash family, which the FBI attributes to their capability, low cost and lack of observable guardrails when a task is framed as penetration testing.
- What to do: Inventory every internet-facing application, restrict cloud administration and publishing interfaces to trusted networks, review Microsoft Entra audit records for new service principals, and hunt the indicators in the alert.
In plain English
ARTEX is a tool that lets attackers write a goal in plain English (for example, get into this company’s database) and then have AI agents automatically carry out the steps to break in. The FBI says criminals have been using it since August 2026 to attack companies around the world, and in some cases they went from starting the attack to having full control in less than three hours. The tool is still available even though the original developer took it down from GitHub, because copies are still circulating.
What you should do: If you run a business with any systems connected to the internet, especially partner portals or employee apps that might not get as much security attention, you should check your logs for the warning signs the FBI lists and make sure those systems are locked down. If you are an ordinary person who does not run servers or cloud systems, you do not need to do anything yourself, but the companies you do business with should be taking action.
What happened
The Federal Bureau of Investigation released FLASH-20261113-001 on 13 November 2026, a TLP:CLEAR alert on the ARTEX autonomous penetration testing framework. The FBI says malicious actors have used ARTEX since at least August 2026 against organizations worldwide across financial services, government, technology, defense, semiconductor, energy, healthcare, manufacturing, telecommunications and legal sectors.
ARTEX is a multi-agent platform written in Go that turns goals written in plain language into machine commands run by its own agents, with little human involvement after the objective is set. The framework ships no model of its own and calls external providers instead. The FBI’s analysis of attacker-controlled instances found Chinese models most prevalent, led by the DeepSeek Flash family, which it attributes to their capability, low cost and lack of observable guardrails when a task is framed as penetration testing. Frontier models from Anthropic and OpenAI are also supported.
The original developer, Autumn-27, removed the GitHub repository on 8 October 2026 after reports of threat actor abuse, but the FBI says the framework still spreads through community forks, localized variations, archived copies and a commercial version called ARTEX PRO. Researchers counted over 1,600 publicly exposed ARTEX consoles in early November 2026.
The FBI alert singles out peripheral systems that receive less security attention than flagship applications: partner and supplier portals, mobile backends, employee applications, sales-support systems, legacy services and third-party integrations. Named campaigns include personal information on about 67,000 individuals at South Korean financial institutions and access to more than 2,250 ConnectWise Cloud Backup downstream tenants.
What you should do
The FBI recommends organizations inventory every internet-facing application, including the peripheral ones, and restrict cloud administration, publishing interfaces such as Kudu and SCM endpoints, hypervisors and backup platforms to trusted networks.
Review Microsoft Entra audit records for new service principals, credential additions and consent grants, and hunt the indicators in the alert. Organizations that authorized the affected ConnectWise applications should review activity from at least 1 October 2026.
Network signs that point to ARTEX activity include outbound calls to LLM endpoints including api.anthropic.com, api.deepseek.com, open.bigmodel.cn and api.x.ai when they appear alongside other suspicious activity. The FBI also lists high-frequency automated requests with sequential enumeration against login and search endpoints, outbound transfers of structured personal data over HTTPS to unauthorized destinations, and .aspx or .jsp web shells in unexpected application paths.
The FBI asks recipients to contact a local field office or the Internet Crime Complaint Center. For ARTEX cases specifically, the alert requests console screenshots and configuration files, service principal sign-in logs, Microsoft Graph and Entra audit records, outbound LLM endpoint connections, cloud and container activity, web shells and other persistence artifacts, and loss and impact figures.
What it means
ARTEX represents a new class of threat in which AI agents automate the entire intrusion lifecycle at machine speed. The FBI’s observation that some intrusions went from initial targeting to privileged access in under three hours shows how agentic frameworks compress timelines that previously required days or weeks of manual work.
The framework’s reliance on external LLM providers, particularly Chinese models with fewer guardrails for penetration testing prompts, demonstrates how the commoditization of capable AI models enables offensive automation. The fact that over 1,600 ARTEX consoles were publicly exposed in early November 2026 suggests widespread adoption despite the original repository’s removal.
The alert’s focus on peripheral systems reflects a shift in attacker targeting. Partner portals, mobile backends and legacy services often receive less security attention than flagship applications but provide equally valuable access once compromised.



