Threat Intelligence

AI Pentesting Tool AntiFox Linked to Attacks That Stole AWS Credentials

The Hacker News · 12 Nov 2026
Key Takeaway Keep internet-facing web applications patched and monitored, and make sure any AWS credentials stored on or reachable from those servers are tightly limited and rotated if you suspect exposure.

Researchers at Arctic Wolf Labs have detailed a campaign in which an emerging AI-driven penetration testing platform called AntiFox was used to steal Amazon Web Services (AWS) credentials and move sideways through compromised environments. In several recent intrusions, Alibaba Cloud systems hosting AntiFox interfaces were linked to confirmed malicious actions against internet-facing web services and the AWS environments connected to them.

AntiFox is available on GitHub, where it has been forked 251 times and starred 474 times. Its maintainer describes it as a multi-agent system that runs a full engagement, from reconnaissance through to report delivery. The observed attacks chained web exploitation with the deployment of web shells (small scripts that give attackers remote control of a server). That access then supported configuration discovery, credential validation, cloud-service enumeration, secret access and storage operations.

Some of the initial access involved a compromised internet-facing Internet Information Services (IIS) application. Arctic Wolf reported that a web shell was created through the IIS worker process, which then ran commands to identify the execution context, list the application directory, check permissions and test whether files could be written to the web root. Arctic Wolf said this pattern suggests the compromise came through the affected web application itself.

AntiFox AWS Web Shell IIS Cloud Security Arctic Wolf

Summarised by CISO AI from The Hacker News, written with Claude Sonnet 5.5. We link back to every original so you can read it yourself.