Hundreds of Artex AI hacking tools found publicly exposed to the web
Security researchers have discovered hundreds of copies of a Chinese-made AI hacking tool publicly exposed to the internet for anyone to access, potentially allowing outsiders to launch cyberattacks against unsuspecting targets.
The hacking software, called Artex, is an open source autonomous penetration testing tool, meaning software that automatically probes computer systems for weaknesses, and it’s been linked to several cyberattacks since its public release in July. As open source software, it’s free for anyone to download and run on their own servers, making it a popular tool for those who cannot access Anthropic or OpenAI’s most advanced cybersecurity AI models for discovering security vulnerabilities. Microsoft has previously described Artex as a system of AI agents that can conduct cyberattacks “from reconnaissance through data exfiltration with little needed human interaction.”
In a blog post, cybersecurity firm Censys, which scans the internet for exposed or vulnerable systems, said that it identified more than 800 distinct deployments of Artex that were accessible from the web without needing a password to log in.
Silas Cutler, principal security researcher at Censys who wrote the blog post, said that not every instance of Artex is operated maliciously and many are used for authorized testers. But it’s unclear why hundreds of these Artex systems are exposed to the web, as the software does not require them to be accessible from the internet.
The findings underscore how even powerful hacking tools can be misconfigured to be publicly accessible by anyone, increasing the chance that someone will find and misuse them. The publicly accessible systems also expose attack tools, such as implants (hidden malicious software) used to compromise and maintain persistent access to a victim’s network.
Security companies have linked the use of Artex to several broad-scale cyberattacks, including against the Korean finance industry in September. Cybersecurity giant CrowdStrike attributed the attacks to a Chinese-speaking hacker who used an Artex instance in the attacks, in part because the hacker had left an “open directory” hosting the system. Censys said that its data showed the Artex instance in question had been publicly exposed for months, and appeared to contain more attack data that extended “well beyond South Korean banks,” including payment and gaming companies.
Artex was also used in an attack on IT support giant ConnectWise earlier in October, which allowed Chinese-linked hackers to spy on thousands of organizations whose data and files are hosted in Microsoft’s cloud. Microsoft, which has visibility into the attack, said in a blog post that the hackers used Artex to break into customers’ cloud environments and steal their data at such speed that defenders had “little time to detect and respond.”
Many of the attacks linked to Artex involved exploiting simple vulnerabilities, such as guessing weak or known passwords, and a lack of multi-factor authentication.
The findings show that simple vulnerabilities, including misconfigurations, can expose both the attacker and their targets.
Artex has since announced it would go closed-source, effectively limiting further releases for paid customers. There are still dozens of copies of Artex’s code available on code-sharing sites that can still be used in active attacks.
https://techcrunch.com/2026/11/06/hundreds-of-artex-ai-hacking-tools-found-publicly-exposed-to-the-web/Reposted. Will be removed on request. All rights belong to the original author.
More from this batch
Meta introduces Spaces, a new way to collaborate with your Muse agent
Meta adds Spaces so Muse can spin up topic-specific trackers and planners that stay synced with connected apps, after Muse Voice and a claim…
Meta 撤回「可疑」商业条款更新:不再强迫 Facebook 主页主人允许 AI 训练外链内容
Ars 标题直译社区吐槽「Meta 以为我们不会读吗」——公司放弃一版被指含糊、可能扩大对关联内容 AI 训练授权的商业条款改动。对品牌与企业主页运营方,是数据授权边界被公开压力扳回的信号;具体条款以 Meta 最新文本为准。
中期选举「蓝潮」之后:AI 产业会不会迎来艰难两年?播客梳理监管与数据中心政治风险
Equity 播客讨论民主党大胜后,公众对数据中心与 AI 的反感如何转化为立法与地方审批压力,以及大厂资本开支叙事可能被改写。偏宏观产业分析,可与本周纳指抛售、数据中心公投新闻交叉阅读;非单一公司公告。
大学图书馆被 AI 爬虫「淹没」:公共访问承压,机构开始限流与封禁
CBC 报道多所大学图书馆系统遭大规模 AI 数据抓取机器人冲击,影响正常读者访问。Hacker News 热议(约 113 分)。对企业与高校:开放知识库、文档站、API 网关都要按「Agent 流量」重新设限流、鉴权与缓存策略,而不只是防传统爬虫。
Teaching AI to build scientific models
Anthropic Science guests argue AI should return distributions of plausible scientific models—and which alternatives failed—not a single best…
Anthropic IPO 买方估值预期压到约 1.1 万亿美元一带(HN 转 Bloomberg)
Hacker News 热帖摘要 Bloomberg:部分潜在买家把估值预期压到约 1.1 万亿美元量级,低于此前约 1.5 万亿叙事。与本周科技股抛售、缺 10 月收入数字等压力同向。细节以彭博原文付费墙为准;作「市场出价下修」信号记录。
Serverless MCP server for AI agent data lake access on Amazon ECS Fargate
AWS NASC team shows a metadata-driven MCP gateway on ECS Fargate so agents query Athena/Redshift via Bedrock without per-table tool code.
SageMaker Inference 支持 MIG:一张 GPU 切成多实例,提高端点利用率
正式支持 NVIDIA Multi-Instance GPU,把单卡划成隔离实例给多模型/多租户端点。偏推理成本与密度优化;托管在 SageMaker(非自托管)。对要把多个中小模型挤进同一硬件池的企业推理平台有直接价值。
Bedrock AgentCore + Okta Cross App Access(其二):把「一个受管 Agent」扩成企业网关模式
接上篇:用 AgentCore Gateway 做企业级扩容,统一治理多应用访问。偏 IAM/身份与 Agent 工具权限;需 AWS + Okta 栈。成熟度:官方教程级,适合已试点 AgentCore、要上生产权限模型的安全/平台组。
Greenlight Financial:在 Bedrock AgentCore 上建自治 SOC,月最高约 4000 单里 90%+ 无需人工
儿童金融科技公司案例:安全与风险工单由 Agent 自动处理,宣称超九成可无人值守闭环。展示 AgentCore 在安全运营场景的成熟度信号;闭源产品集成,非可自托管开源 SOC。对金融合规团队可作对标,需自行核实指标口径。
Taxbit Assist:带引用、按角色权限的企业税务 Agent,嵌在仪表盘里跑在 AgentCore 上
税务合规 SaaS 把助手嵌进控制台:回答带出处、按角色可见数据。强调 grounded + permission-aware,而非裸聊天。商业 SaaS 功能,非开源;对企业「受控 RAG Agent」落地形态是清晰样板。
把 Claude Code 接到 Bedrock AgentCore 远程会话:隔离沙箱 + 安全控件
每项编码任务在客户账户隔离会话中跑,延长 Claude Code 到远程 Agent。适合已用 Claude Code、又要企业网络隔离与审计的团队;依赖 Bedrock/AgentCore,非本地私有化。集成有一定门槛(会话、权限、网络策略)。