AIToday
AI Safety & AlignmentOpen-Source AITechCrunch AIPublished: Nov 7, 2026, 04:00 JST

Censys finds 800+ exposed Artex AI hacking tool deployments

Send on LINE
Censys finds 800+ exposed Artex AI hacking tool deployments

3 Key Points

  1. What happened

    Cybersecurity firm Censys said it identified more than 800 distinct deployments of Artex, an open-source autonomous penetration testing tool, accessible from the web without a password.

  2. Why it matters

    The software does not require internet access, so the exposure looks like misconfiguration, raising the chance outsiders find and misuse these systems, which also host implants used for persistent network access.

WHO IT HITSSecurity teams at organizations running or assessing AI-driven penetration testing tools may need to check whether their Artex instances are unintentionally reachable from the internet, since exposed systems can leak attack tools and implants.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

Context & Analysis

Artex emerged as a free alternative for security professionals who cannot access the most advanced cybersecurity AI models from Anthropic or OpenAI. Its open-source nature made it easy to download and run, but also easy to misconfigure. Censys's finding that more than 800 deployments are reachable without a password suggests many users left the tool exposed, even though it does not need to be internet-accessible. That exposure matters because the same systems can host implants and other attack tools, effectively lowering the barrier for anyone who finds them. The tool has already been tied to real-world incidents: CrowdStrike attributed a September attack on the Korean finance industry to a Chinese-speaking hacker who used an Artex instance, and Microsoft reported that hackers used Artex in an October breach of ConnectWise to steal data from cloud environments at high speed. Many of those attacks exploited simple weaknesses like weak passwords and missing multi-factor authentication. Artex's move to closed-source may slow new releases, but copies of its code remain on code-sharing sites and can still be used in active attacks.

FAQ
What is Artex?
Artex is an open-source autonomous penetration testing tool linked to several cyberattacks since its public release in July. Microsoft described it as a system of AI agents that can conduct cyberattacks from reconnaissance through data exfiltration with little human interaction.
Why are exposed Artex systems a concern?
The software does not require internet access, so hundreds of publicly accessible instances are likely misconfigured. These systems also expose attack tools such as implants used to compromise and maintain persistent access to victim networks.
Has Artex been used in real attacks?
Yes. Security companies linked Artex to attacks on the Korean finance industry in September and on IT support giant ConnectWise in October, where hackers spied on thousands of organizations hosted in Microsoft's cloud.
Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleSan Francisco daters filter matches with 'Fuck AI' on Hinge