Skip to main content
Live
Main content

Censys finds 1,465 hosts exposing ARTEX AI hacking consoles online

About 815 deployments look distinct, and some left open directories holding exploit kits, implants and an operator's shell history.

Jaeden Schafer
Editor in Chief · · 4 min read
Censys finds 1,465 hosts exposing ARTEX AI hacking consoles online

Internet scanning firm Censys has found 1,465 hosts running publicly exposed consoles for ARTEX, an open-source AI agent framework for autonomous penetration testing that has been tied to attacks on South Korean banks and the ConnectWise Cloud Backup supply-chain compromise. Censys published the count, current as of November 4, in a research post on November 5.

About 650 of those hosts sit in two blocks of identically configured servers, leaving roughly 815 deployments that look distinct. Censys said the uniform setups point to a provisioning template rather than hundreds of individual operators. Because the ARTEX console does not need to face the public internet at all, the firm said the true number of deployments is likely higher.

The United States hosted the most exposed consoles at 726, followed by Hong Kong with 387, China with 177, Japan with 51, Singapore with 38 and South Korea with 21. PEG Tech's network accounted for 493 hosts across 13 address blocks, and Yancy Limited for 157. Censys said 155 ARTEX hosts, or 10.6%, also ran at least one other tool it tracks as a threat, including Cobalt Strike, Vshell and Adaptix C2.

Key facts

  • 01Censys counted 1,465 hosts running exposed ARTEX consoles as of November 4, 2026.
  • 02About 650 hosts sit in two identical hosting blocks, leaving roughly 815 distinct-looking deployments.
  • 03The US hosted 726 exposed consoles, Hong Kong 387 and China 177.
  • 04155 ARTEX hosts, or 10.6%, also ran other threat tools such as Cobalt Strike and Vshell.
  • 05Microsoft tied ARTEX to Storm-0940's ConnectWise compromise, with sign-in attempts against more than 2,250 tenants.

ARTEX was published on GitHub by a user named Autumn-27 on July 26, 2026, under the AGPL-3.0 license. It is written in Go with a Next.js console, splits work between planner and worker agents, and can run on models from Anthropic, OpenAI or any OpenAI-compatible endpoint. Autumn-27 also wrote ScopeSentry, an asset-discovery platform with more than 2,000 GitHub stars, and ARTEX collected an estimated 1,500 to 2,000 stars within ten weeks.

Some deployments exposed their operators' toolkits along with the console. Censys counted 32 open directories on ARTEX hosts while writing the post, holding exploit binaries, a Windows lateral-movement kit, implant builds, the private key for a man-in-the-middle root certificate authority and one operator's home directory, including SSH files and shell history. Between November 3 and November 5, 10 of those directories closed and 15 new ones appeared.

ARTEX first drew wide attention in an October 7 CrowdStrike report on an actor who targeted a South Korean finance company from late September into early October, breaching a broker-facing loan inquiry service at one bank and an employee mobile system at another. That ARTEX instance ran DeepSeek v4.1-flash as its main model. Censys said the server CrowdStrike identified had exposed open directories since August 18, seven weeks before the report, with attack data reaching beyond South Korean banks to payment and gaming companies.

On October 21, Microsoft attributed the ConnectWise Cloud Backup compromise to Storm-0940, which it describes as a China state-aligned actor active since 2021. Microsoft said the group used ARTEX for scanning, password spraying and OAuth abuse, attempting sign-ins to more than 2,250 tenants at a peak of 2,900 attempts per minute, and some victims saw privileged cloud access taken in under three hours.

Many of the attacks linked to ARTEX relied on weak or known passwords and on accounts that lacked multi-factor authentication.

Related · from this week
OpenAI safety veteran David Robinson resigns, says culture is 'broken'
Jaeden Schafer · 4 min read →

Censys said not every ARTEX instance is run with malicious intent, and many are likely used by authorized testers. The day after CrowdStrike's report, Autumn-27 posted a statement denying involvement in the attacks, saying ARTEX was meant for testing within authorized scopes and that the project would go closed-source with no further releases. The repository has since been taken down, but archived copies, translations and rebrands such as ScopeWeaver still circulate.

Censys published a detection query keyed to the console's page title and static assets, and added ARTEX and ScopeWeaver threat labels to its platform so defenders can hunt for deployments. The console listens on port 8787 by default.

ShareXLinkedInEmail
AI Box

Every AI model. One chat.

The latest models from ChatGPT, Claude, Gemini, Sora, ElevenLabs — 80+ models in a single chat. Compare answers side by side. Pick the best one every time.

  • ChatGPT, Claude, Gemini, Grok, DeepSeek — in one chat
  • Generate images & video with Sora, Veo, Ideogram
  • Compare any two models side by side
  • From $8.99/mo · 80+ models, all included
Try AI Boxaibox.ai
Trusted by 3,000+ teams
Got a tip?

Working on something we should cover, or seeing a story we missed? Send leads, documents, or feedback to hello@aichatdaily.com. For sensitive tips, see our secure tips page for Signal and PGP options.

Spotted an error? Email hello@aichatdaily.com with the URL and the issue, or read our full corrections policy.

AI Box Daily briefingFree · Daily · No fluff

Stay ahead of everyone in AI.

The tightly edited AI news email engineers, founders, and investors actually open. One email. Every weekday. Five minutes to finish.

Loved by 10,000+ AI professionals
Free forever. Unsubscribe with one click.

The briefing read inside teams at

Keep reading

More from Security

OpenAI logo
Security

OpenAI safety veteran David Robinson resigns, says culture is 'broken'

Robinson, who led safety reports for major product launches over 3.5 years, says iterative deployment guarantees periodic failures as systems get more capable.

Jaeden Schafer4 min read
Nvidia logo
Security

Nvidia opens OpenShell and Sentry to contain rogue AI agents

The chipmaker is pushing an open-source Agent Safety Platform as frontier labs disclose agents hacking Hugging Face and probing government sites.

Jaeden Schafer4 min read
Anthropic logo
Security

DC Circuit upholds Trump blacklist of Anthropic in 2-1 ruling

Appeals court says Pentagon can designate Anthropic a supply chain risk for restricting Claude features, even absent malicious intent.

Jaeden Schafer5 min read