3 Sources
[1]
Hackers use AntiFox AI agents in AWS credential-theft attacks
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,
[2]
AntiFox AI Pentesting Platform Linked to Attacks That Accessed AWS Production Secrets
Cybersecurity researchers have disclosed details of a campaign in which an emerging agentic penetration testing platform called AntiFox has been used to steal Amazon Web Services (AWS) credentials and pivot laterally into compromised environments. "In several recently observed intrusions, Alibaba
[3]
AntiFox AI agents hijacked by hackers to carry out theft of AWS credentials
* Attackers are abusing the AI-powered penetration testing tool AntiFox to search for credentials and compromise AWS environments * Campaigns leveraged web-server intrusions and stolen cloud credentials to map infrastructure and access sensitive resources * Researchers urge organizations to
Share
Copy Link
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.
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 secrets2
. 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 vulnerabilities1
.
Source: BleepingComputer

Source: TechRadar
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 directory2
. The webshell was created using w3wp.exe, the IIS worker process, suggesting compromise through the affected web application itself2
. After gaining initial access, attackers attempted to connect to an internal production database using credentials extracted from the application configuration2
.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 minutes1
. 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 Bedrock2
. While most authenticated cross-service API requests ended with AccessDenied errors, some discovery and secret-access operations succeeded2
. In at least some instances, the activity progressed beyond Secrets Manager enumeration to successful GetSecretValue requests against production secrets2
.
Source: Hacker News
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 operations2
. 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 attacks2
.Related Stories
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 times2
. 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 restrictions1
. 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 banks1
. CrowdStrike also linked ARTEX to a cyberespionage campaign in which the Chinese hacking group Vapor Panda targeted more than 200 organizations across 14 countries1
.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 files1
. 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 minutes2
. 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.Summarized by
Navi
[1]
[2]
16 Nov 2026•Technology

21 Feb 2026•Technology

02 Sept 2026•Technology
