Security researchers at Censys have identified more than 800 publicly exposed deployments of Artex, a Chinese-made AI-powered penetration testing tool, accessible from the internet without password protection, according to a company blog post published November 6.
Artex is an open-source autonomous penetration testing system that automatically probes computer systems for weaknesses. Released publicly in July, the software has been linked to several cyberattacks. Microsoft has described Artex as a system of AI agents capable of conducting cyberattacks “from reconnaissance through data exfiltration with little needed human interaction.”
Silas Cutler, principal security researcher at Censys, wrote in the blog post that while not every Artex instance is operated maliciously—many are used by authorized testers—it remains unclear why hundreds of these systems are exposed to the web, since the software does not require internet accessibility to function.
The exposed systems also reveal attack tools including implants, which are hidden malicious software used to compromise and maintain persistent access to victim networks.
Security companies have attributed Artex use to multiple cyberattacks. CrowdStrike linked the tool to attacks against the Korean finance industry in September, attributing them to a Chinese-speaking hacker who used an Artex instance with an “open directory” hosting the system. According to Censys data, that Artex instance had been publicly exposed for months and appeared to contain attack data extending “well beyond South Korean banks,” including payment and gaming companies.
Artex was also used in an attack on IT support company ConnectWise in October, according to the report.
As open-source software, Artex is free to download and run on individual servers, making it popular among users who cannot access advanced cybersecurity AI models from Anthropic or OpenAI for discovering security vulnerabilities.