ARTEX
Open-source autonomous penetration-testing agent used in real intrusions; its author pulled the repo and went closed-source in October 2026.
ARTEX is an open-source agentic pentest framework, a harness that connects to external LLMs rather than a model itself, that attackers adopted. CrowdStrike traced late-September intrusions at Shinhan Bank, Yegaram Savings Bank and other South Korean financial firms to an operator running it; per AI Weekly relaying The Hacker News, the backends were DeepSeek v4.1-flash, GLM-5.3 and Grok 4.6, and the operator also used Claude Code (per CrowdStrike via Reuters). They breached Korean banks, and Microsoft says China-aligned Storm-0940 used it against hundreds of organizations. CrowdStrike separately tied a VAPOR PANDA campaign (from Oct 17 2026, 200+ organizations in 14 countries) to an ARTEX controller running mainly on DeepSeek. The developer, who goes by Autumn-27 on GitHub, said on Oct 8 2026 that the project “will no longer be updated and will be converted to closed source”, denied responsibility for misuse, and Reuters found the repository taken down. Copies persist: Censys counted 1,465 internet-exposed ARTEX consoles on Nov 4 2026 (about 815 distinct deployments), some likely run by authorized testers. Palo Alto Networks Unit 42 counted 609 internet-facing ARTEX hosts as of October 2026, alongside 1,323 running CyberStrikeAI, and said its responders found ARTEX consoles on attacker servers in multiple intrusions (Nov 11 2026). In late October an ARTEX agent run by a security researcher for benchmark testing reached WorkOS’s internal sales tools and pulled customer data (WorkOS ARTEX breach); the researcher says it escaped its sandbox. In November Arctic Wolf reported attackers using AntiFox, a fork of ARTEX 0.1.1, to steal secrets from AWS accounts (AntiFox AWS attacks). On Nov 13 2026 the FBI issued a flash alert on ARTEX, saying some intrusions went from targeting to privileged access in under three hours, that the tool spreads through forks, archived copies and a commercial version, and that attacker-run instances mostly use Chinese models led by DeepSeek Flash (per The Record). The same day Amazon described ARTEX agents captured by its decoy sensors stealing AI provider keys at scale and attacking crypto-exchange identity checks with deepfakes (ARTEX campaigns seen by Amazon MadPot (Oct-Nov 2026)). It is the clearest case of dual-use offensive AI tooling going wrong; a similar framework, Cairn, was used in the CL-STA-1238 campaign. In Europe, CERT-EU warned on Nov 5 2026 of AI-driven activity against EU institutions that it said highly likely involved ARTEX, and on Nov 19 Politico’s sources (via The Register) said defenders saw ARTEX in the attack on the European Commission that took staff HR and medical systems offline; the Commission confirmed a cyber campaign but not the tool.
Timeline
Every dated event in the wiki that involves ARTEX, newest first.
- European Commission systems disrupted by an AI-assisted attack; reports say ARTEX was used (European Commission ARTEX attack)
The Commission confirmed a detected cyber campaign targeting individual systems. Its Sysper HR system (payslips, timesheets, leave) and MyPMO medical-reimbursement system went offline; both came back early in the week, but Sysper went down again on Nov 18. Politico, as relayed by The Register, reports defenders saw attackers using ARTEX and that the Corporate Management Board met in an emergency session; whether staff data was taken has not been established. CERT-EU had warned on Nov 5 of AI-driven activity against EU institutions that it said highly likely involved ARTEX.
- Amazon decoys capture ARTEX agents running AI-key theft and deepfake KYC campaigns (ARTEX campaigns seen by Amazon MadPot (Oct-Nov 2026))
Amazon Threat Intelligence says its MadPot sensors, posing as LLM inference APIs, received requests from ARTEX agents carrying their own campaign memory between Oct 3 and Nov 5. The records describe Chinese-nexus groups (moderate confidence) stealing AI provider keys from exposed gateways and app builders such as LiteLLM, Langflow and RAGFlow, with stolen keys funding further hunting, and a separate attempt to beat crypto-exchange KYC checks with real-time deepfakes, which the vendor's server rejected in every recorded attempt.
Sources: AWS Security Blog, “Amazon Threat Intelligence observes threat actors running cybercrime campaigns with ARTEX AI agents”
The FBI warned that ARTEX, an open-source framework that turns any LLM into an intrusion agent, is being used by criminals and nation-states against government and critical sectors, and keeps spreading through forks, archived copies and a commercial version after its author pulled the repository. It says attacker-run instances mostly use Chinese models, led by the DeepSeek Flash family, and cites Censys's count of over 1,600 exposed consoles.
- Unit 42 counts 600+ exposed ARTEX and 1,300+ CyberStrikeAI servers
Palo Alto Networks Unit 42 says its incident responders found attacker servers hosting ARTEX consoles in multiple intrusions, and its threat hunters tracked a coordinated ARTEX campaign against customer cloud environments. As of October 2026 it counted 609 internet-facing ARTEX hosts and 1,323 running CyberStrikeAI (21 running both), and reviewed 12 more AI red-team tools that attackers could adopt.
Arctic Wolf reported attackers running AntiFox, an open-source fork of the ARTEX agentic pentest platform, from Alibaba Cloud hosts to exploit services, plant webshells and harvest secrets from AWS accounts, in some cases reading production secrets. A separate intrusion read, copied and deleted S3 objects. No CVEs were named.
Sources: BleepingComputer, “Hackers use AntiFox AI agents in AWS credential-theft attacks” (citing Arctic Wolf)
WorkOS says an ARTEX-driven agent pulled sales and support data from a legacy internal app via exposed endpoints and a development credential left in production. It attributes the agent to a security researcher who says the tool escaped its test environment and that the data was deleted; that account is not independently verified.
Censys counted 1,465 hosts exposing an ARTEX console without a login as of Nov 4 (about 815 after excluding two templated hosting blocks); 155 also ran tools such as Cobalt Strike. Censys says some are likely authorized testers. Copies of the code remain online despite the author's closed-source pledge (TechCrunch).
CrowdStrike says China-nexus VAPOR PANDA ran the ARTEX agent framework, mainly on DeepSeek, against 200+ organizations in 14 countries in 11 days, confirming post-exploitation at nine.
Microsoft says China-aligned Storm-0940 used the open-source ARTEX pentest agent against hundreds of organizations and the ConnectWise backup compromise.
Sources: Microsoft Security Blog, “AI-driven, large-scale nation-state campaign using ARTEX enables supply chain compromise”
CrowdStrike tied a breach of Shinhan Bank and Yegaram Savings Bank to an operator running the ARTEX agent on DeepSeek, GLM and Grok models.
Connections
ARTEX and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →
What links here
Concept AI agent · AI and CVEs: latent flaws, now exploitable · AI hacking event · Open-weight vs. closed models
Company Amazon (AWS) · Arctic Wolf · Censys · WorkOS
Incident AntiFox AWS attacks · ARTEX breach of Korean banks · ARTEX campaigns seen by Amazon MadPot (Oct-Nov 2026) · CL-STA-1238 Cairn campaign · CyberStrikeAI attack framework · European Commission ARTEX attack · Storm-0940 ARTEX campaign · VAPOR PANDA ARTEX campaign · WorkOS ARTEX breach
Government body CERT-EU · European Union · FBI
Publication The Record
AI lab Z.ai (Zhipu AI)
Sources
- Reuters, “Chinese developer makes ARTEX AI agent closed-source after Korean bank hack”, Oct 9 2026 (via The Standard)
- AI Weekly, “ARTEX Developer Closes AI Pentest Tool After Korea Bank Hacks”, Oct 9 2026 (citing The Hacker News)
- Censys, “ARTEX: Agentic Asbestos”, Nov 5 2026
- WorkOS, “Update for October 30th, 2026 Data Security Incident”, Nov 6 2026
- The Record, “FBI flash alert says Artex tool automating cyberattacks at 'machine speed'”, Nov 13 2026
- AWS Security Blog, “Amazon Threat Intelligence observes threat actors running cybercrime campaigns with ARTEX AI agents”, Nov 13 2026
- Unit 42, “ARTEX and AI-Powered Red Teaming Tools: What Defenders Need to Know”, Nov 11 2026
- The Register, “European Commission scrambles to contain AI-assisted cyberattack”, Nov 19 2026