Cybersecurity researchers discovered attackers using Alibaba Cloud to host AntiFox AI, an open-source penetration testing platform, to automate AWS credential theft. The AI-driven cyberattacks successfully accessed production secrets through webshell deployment and rapid-fire API requests across multiple cloud services.

Attackers Deploy AntiFox AI on Alibaba Cloud for Automated Attacks

Cybersecurity researchers at Arctic Wolf uncovered a sophisticated campaign where threat actors weaponize AntiFox AI, an open-source AI penetration testing platform, to target web services and AWS environments

1

. The infrastructure hosting AntiFox was observed on Alibaba Cloud, conducting malicious activities including vulnerability exploitation, webshell deployment, credential validation, configuration discovery, and harvesting of AWS production secrets

2

. Originally created as a fork of ARTEX 0.1.1, AntiFox features a Chinese-language interface that enables users to deploy AI agents and automate common penetration testing tasks such as mapping exposed services and probing target endpoints for vulnerabilities

1

.

Source: BleepingComputer

Source: BleepingComputer

Source: TechRadar

Source: TechRadar

How AI-Driven Cyberattacks Steal AWS Credentials Through Webshell Deployment

One documented case revealed attackers deploying an ASPX webshell on an internet-exposed IIS server, executing operating system commands to access application settings and database connection strings

1

. The threat actors ran PowerShell commands to locate web.config files and configuration backups, read application settings, enumerate debug and error-log directories, and copy configuration and log files to a web-accessible directory

2

. The webshell was created using w3wp.exe, the IIS worker process, suggesting compromise through the affected web application itself

2

. After gaining initial access, attackers attempted to connect to an internal production database using credentials extracted from the application configuration

2

.

Rapid-Fire API Requests Target Multiple AWS Services

The attackers used valid IAM credentials and EC2 roles to probe Amazon Web Services endpoints with alarming speed and scale

1

. In one intrusion, they cycled through multiple identities and made hundreds of API requests in approximately 30 minutes

1

. The reconnaissance phase involved enumerating dozens of services, including IAM, EC2, S3, Lambda, Secrets Manager, KMS, RDS, ECS, EKS, Redshift, Athena, Glue, Systems Manager, API Gateway, CloudWatch, CloudFormation, DynamoDB, and Amazon Bedrock

2

. While most authenticated cross-service API requests ended with AccessDenied errors, some discovery and secret-access operations succeeded

2

. In at least some instances, the activity progressed beyond Secrets Manager enumeration to successful GetSecretValue requests against production secrets

2

.

Source: Hacker News

Source: Hacker News

Misuse of AI Agents Enables Lateral Movement and Data Access

In a separate incident, attackers used a valid AWS identity to read, copy, and delete S3 objects, demonstrating successful lateral movement within compromised environments

1

. Arctic Wolf observed that the campaign chained together web exploitation and webshell deployment to facilitate configuration discovery, credential validation, cloud-service enumeration, secret access, and storage operations

2

. According to Arctic Wolf, agentic frameworks like AntiFox make penetration testing techniques more accessible to threat actors while increasing the speed and consistency with which these techniques can be applied in live attacks

2

.

AntiFox Remains Available Despite Weaponizing AI Tools in Attacks

As of now, AntiFox remains available on GitHub, where it has been updated to version 2.0, which improves how the tool documents and reports findings

1

. The project has been forked 251 times and starred 474 times

2

. While its publishers prohibit using the tool against live systems, in real-world penetration tests or security exercises, or for destructive or illegal activity, they do not describe any technical controls that enforce those restrictions

1

. The AntiFox findings follow recent attacks involving ARTEX AI, another agentic penetration testing framework developed in China that went closed-source after being used in attacks on South Korean banks

1

. CrowdStrike also linked ARTEX to a cyberespionage campaign in which the Chinese hacking group Vapor Panda targeted more than 200 organizations across 14 countries

1

.

What Organizations Should Watch For

Arctic Wolf recommends correlating IIS webshell activity with unusual AWS access and reviewing successful API calls within bursts of denials

1

. Defenders should revoke affected AWS sessions and keys and rotate credentials exposed through application files

1

. The integration of AI has allowed adversaries to adapt established tradecraft and deploy them at machine speed, making it possible to progress from scanning GitHub for secrets to exfiltrating data from an Azure Key Vault in five minutes

2

. Organizations must monitor for unusual patterns of API activity, especially rapid sequences of requests across multiple AWS services, and implement stricter controls around credential storage in application configuration files.

© 2026 TheOutpost.AI All rights reserved