Hackers Deploy AntiFox AI Agents on Alibaba Cloud to Steal AWS Credentials

Attackers are hosting self-managed instances of the open-source AntiFox agentic penetration testing platform on Alibaba Cloud to target web services and AWS environments. The infrastructure has been linked to vulnerability exploitation, webshell deployment, credential validation, configuration discovery, and AWS secret harvesting. Originally forked from ARTEX 0.1.1, AntiFox features a Chinese-language interface and allows users to deploy AI agents that automate mapping of exposed services and probing endpoints for vulnerabilities. Arctic Wolf researchers observed malicious activity where valid AWS IAM users and assumed EC2 roles were used to make hundreds of authenticated API requests, resulting in the theft of production secrets in some cases. Separate incidents involved reading, copying, and deleting S3 objects using compromised identities. The findings connect AntiFox to prior ARTEX-linked campaigns, including those attributed to the Chinese group Vapor Panda targeting over 200 organizations. AntiFox remains publicly available on GitHub with version 2.0 updates, despite publisher warnings against illegal use.

BleepingComputerTranslated from English

Read at source

Attackers are using Alibaba Cloud to host self-managed instances of AntiFox, an open-source agentic penetration testing platform, to target web services and AWS environments. The infrastructure hosting AntiFox was used for various malicious activities, including vulnerability exploitation, webshell deployment, credential validation, configuration discovery, and AWS secret harvesting.

Initially created as a fork of ARTEX 0.1.1, AntiFox has a Chinese-language interface and lets users deploy AI agents and automate common penetration-testing tasks, such as mapping exposed services and probing target endpoints for vulnerabilities. Security researchers at Arctic Wolf observed malicious AntiFox-linked infrastructure hosted on Alibaba Cloud using valid AWS identities, including IAM users and, in some cases, assumed EC2 roles, to make authenticated requests to Amazon Web Services APIs.

“In several recently observed intrusions, Alibaba Cloud systems hosting AntiFox interfaces were associated with confirmed malicious actions against internet-facing web services and associated AWS environments,” Arctic Wolf says. One case highlighted in the report involved deploying an ASPX webshell on an internet-exposed IIS server, executing OS commands, accessing application settings and database connection strings, and copying configuration and log files to a web-accessible directory. The attacker also used valid IAM credentials and EC2 roles to probe Amazon Web Services (AWS) endpoints.

In one intrusion, they cycled through multiple identities and made hundreds of API requests in about 30 minutes, the researchers note. Although most of these attempts were blocked, the attacker was successful in some cases and obtained production secrets. In a separate incident, the attackers used a valid AWS identity to read, copy, and delete S3 objects.

Arctic Wolf's report includes hunting guidance and recommendations for defenders that include correlating IIS webshell activity with unusual AWS access and reviewing successful API calls within bursts of denials. The researchers also recommend revoking affected AWS sessions and keys and rotating credentials exposed through application files.

The AntiFox findings follow recent attacks involving ARTEX AI, another agentic penetration-testing framework developed in China that went closed-source after it was used in attacks on South Korean banks. CrowdStrike also linked ARTEX to a cyberespionage campaign in which the Chinese hacking group Vapor Panda targeted more than 200 organizations across 14 countries.

For now, AntiFox remains available on GitHub, where it has been updated to version 2.0, which improves how the tool documents and reports findings. Its publishers prohibit using the tool against live systems, in real-world penetration tests or security exercises, or for destructive or illegal activity, but they do not describe any technical controls that enforce those restrictions.

Meridian digestThe week's most consequential security stories, distilled into one briefing.See the digest

More in AI & Model Risk

Researchers Show Malicious Webpage Could Hijack Meta Muse AI Agent and Extract Private Conversations
China-Linked Actors Use Autonomous AI Agents to Discover Zero-Day Path Traversal in MONAI Label and Achieve Root Access
AI & Model Risk

China-Linked Actors Use Autonomous AI Agents to Discover Zero-Day Path Traversal in MONAI Label and Achieve Root Access

Suspected China-linked hackers deployed autonomous AI agents powered by the open-source Cairn framework to identify and exploit a previously unknown path traversal vulnerability in MONAI Label, an open-source medical imaging server used by research teams. The flaw, tracked as CVE-2026-133968 and rated 9.8, affects versions 0.8.5 and earlier by allowing unauthenticated attackers to write files outside the designated storage directory when authentication is disabled by default. Amazon Threat Intelligence reconstructed the campaign after discovering an exposed Cairn control panel that revealed the agents' prompts, task settings, and execution history spanning roughly 48 hours in September. Within about 11 minutes the agents mapped the application and achieved arbitrary file writes; in a follow-up session they planted a malicious Python startup file that was loaded during a training job, granting root access on a university server. Maintainers merged a source-code fix on October 19 that enforces path resolution inside approved folders, yet no patched release has been published and the latest available version remains 0.8.5 from 2024. Amazon attributes the activity to a China-linked operator with moderate confidence based on Simplified Chinese prompts and China Standard Time settings, though no specific group or government sponsorship was confirmed.

The Hacker NewsNov 21, 2026Translated from English

Chinese-Linked Actors Use Cairn AI Platform to Discover and Exploit MONAI Label Zero-Day