Skip to main content
Mallory
← Back to News
ai-enabled-threat-activitycredential-access-methodinitial-access-methoddata-exfiltration-method

Attackers Abuse AntiFox AI Agents to Access AWS Secrets and Delete S3 Objects

Emerging Technology Risk · 14 sources · Updated 3d ago · First seen Nov 11, 2026

Attackers Abuse AntiFox AI Agents to Access AWS Secrets and Delete S3 Objects

Attackers are abusing self-managed instances of AntiFox, an open-source AI-driven penetration-testing platform hosted on Alibaba Cloud, to compromise internet-facing web applications and associated AWS environments. Arctic Wolf Labs observed IIS compromise, ASPX web shell deployment, configuration and credential discovery, and cloud-service enumeration. Intruders used valid IAM user credentials and assumed EC2 roles to make authenticated AWS API calls, including successful Secrets Manager requests that exposed production secrets. A separate incident involved reading, copying, and deleting Amazon S3 objects.

The vulnerability used to compromise IIS and the source of AWS credentials in some attacks remain unknown. The activity illustrates how agentic tools can accelerate established intrusion techniques, but does not establish that every attack step was autonomous. Defenders should correlate IIS web shell activity with unusual AWS access, investigate successful API calls even when surrounded by denied requests, and revoke compromised sessions and credentials. Reviews should prioritize Secrets Manager access and S3 object operations to determine whether attackers exposed secrets or altered cloud data.

New surface, new adversariesTrack how attackers are adapting to this technology.
Track this risk
Event timeline

How this story unfolded

Events from the most recent confirmed update back to the earliest known activity.

13 events · Nov 4, 2026 – Nov 10, 2026
  1. Reported Nov 12, 20265d ago

    GitGuardian testing finds ARTEX discovers eight of nine planted credentials

    GitGuardian's separate testing found that an ARTEX build without a dedicated secrets scanner discovered eight of nine planted credentials using ordinary commands. The build began searching within six to thirteen seconds.

    Hackers Abuse AntiFox AI Pentesting Tool to Deploy Webshells and Access AWS Production Secrets
  2. Reported Nov 12, 20265d ago

    AWS says AntiFox-linked intrusions used stolen credentials, not a service compromise

    AWS told BleepingComputer that its services were not compromised and operated as designed. It said attackers accessed customer accounts using credentials stolen from compromised customer applications.

    Hackers Abuse AntiFox AI Pentesting Tool to Deploy Webshells and Access AWS Production Secrets | Cryptika Cybersecurity
  3. Reported Nov 11, 20266d ago

    ARTEX certificate-theft campaign harvests more than 300 Apple certificates

    A reported ARTEX campaign harvested more than 300 Apple code-signing certificates and their passwords. Agents checked certificate passwords, private keys, revocation status, expiration dates, and provisioning profiles; three certificates passed full validation and potentially enabled arbitrary iOS application signing.

    AntiFox AI Pentesting Platform Linked to Attacks That Accessed AWS Production Secrets
  4. Reported Nov 11, 20266d ago

    Check Point finds 2,557 ARTEX hosts and 10 exposed databases

    Check Point Research identified 2,557 systems hosting ARTEX, including 10 misconfigured instances exposing their full databases. Researchers observed operators assigning objectives to agents and largely limiting subsequent human involvement to progress checks and priority changes.

    AntiFox AI Pentesting Platform Linked to Attacks That Accessed AWS Production Secrets
  5. Reported Nov 11, 20266d ago

    VECERT reports AI-assisted theft affecting more than 5,000 students

    VECERT reported that a Chinese threat actor's Operation Ghost-Campus stole data belonging to more than 5,000 students at the Fengxian Campus. The operation used AI agents to find misconfigured servers, extract OpenAI and DeepSeek API keys, and abuse stolen computing resources for academic-fraud tools and student-data extraction.

    AntiFox AI Pentesting Platform Linked to Attacks That Accessed AWS Production Secrets
  6. Reported Nov 11, 20266d ago

    Arctic Wolf links web and AWS intrusions to AntiFox infrastructure

    Arctic Wolf linked self-managed AntiFox interfaces hosted on Alibaba Cloud to confirmed malicious activity against internet-facing web services and associated AWS environments. The observed activity included exploitation, web shell deployment, credential validation, configuration discovery, and secret harvesting.

    Hackers use AntiFox AI agents in AWS credential-theft attacks
  7. Reported Nov 11, 20266d ago

    Separate AWS intrusion reads, copies, and deletes S3 objects

    In a separate incident, attackers used a valid AWS identity to discover S3 resources and read, copy, and delete objects.

    Hackers use AntiFox AI agents in AWS credential-theft attacks
  8. Reported Nov 11, 20266d ago

    Successful AWS Secrets Manager requests expose production secrets

    Although most observed AWS API requests were denied, some discovery and secret-access operations succeeded. Arctic Wolf observed successful Secrets Manager GetSecretValue requests against a production secret.

    Hackers use AntiFox AI agents in AWS credential-theft attacks
  9. Reported Nov 11, 20266d ago

    Attackers use valid AWS identities for rapid cross-service enumeration

    AntiFox-linked infrastructure made authenticated AWS requests using valid IAM credentials and, in some cases, assumed EC2 roles. In one intrusion, attackers cycled through multiple identities and issued hundreds of API requests in approximately 30 minutes; the origin of credentials in some attacks remained unknown.

    Hackers use AntiFox AI agents in AWS credential-theft attacks
  10. Reported Nov 11, 20266d ago

    IIS intruders extract configuration credentials and stage files for access

    Attackers searched application configurations and backups for settings and database connection strings, then attempted to access an internal production database using an extracted credential. They also copied configuration and log files into a web-accessible upload directory.

    Hackers use AntiFox AI agents in AWS credential-theft attacks
  11. Reported Nov 11, 20266d ago

    Attackers compromise an internet-facing IIS application and deploy a web shell

    An IIS worker process created an ASPX web shell that attackers used to execute operating-system commands, enumerate application directories, and check permissions and write access. Arctic Wolf did not identify the vulnerability that enabled the initial code execution.

    Hackers use AntiFox AI agents in AWS credential-theft attacks
  12. Nov 10, 20268d ago

    Arctic Wolf publishes AntiFox infrastructure and intrusion indicators

    Arctic Wolf's November 10 report identified 47[.]79[.]4[.]33 and 8[.]208[.]101[.]210 as AntiFox-linked infrastructure and supplied interface fingerprints, web-shell file patterns, and AWS API sequences for detection. It cautioned that AntiFox is publicly available and cloud infrastructure may be shared or reassigned.

    wolf-tools/pack_alerts/202611-antifox-alibaba-hosted-platforms-facilitate-web-cloud-intrusions at main · rtkwlf/wolf-tools · GitHub
  13. Nov 4, 202614d ago

    Censys identifies 1,465 internet-exposed ARTEX consoles

    Censys identified 1,465 hosts exposing ARTEX consoles as of November 4, 2026, primarily across the United States and several Asian jurisdictions. The finding did not establish that all exposed instances were malicious.

    AntiFox AI Pentesting Platform Linked to Attacks That Accessed AWS Production Secrets
Linked entities

Related entities

Vulnerabilities, threat actors, malware, products, organizations, breaches, and observables Mallory has linked to this story. Indicator values are masked here and available in full in the app.

Open in app →

Malware

1 linked

Affected products

5 linked
Internet Information ServicesAmazon Simple Storage ServiceAmazon Web ServicesAws-Secrets-ManagerAws

Organizations

1 linked
Amazon Web Services

Observables

3 linked

Indicator values are masked on this page. See the values in Mallory Domains, IPs, hashes, and URLs are exportable to your SIEM.

Do you run this?Follow how adversaries are adapting to this technology, and where it touches your stack today.
Track This Risk
Mallory platform

See the full picture, correlated to your attack surface.

This page covers what’s public. Mallory adds the parts that aren’t: which of your assets are affected, which threat actors are using it right now, and what to deploy next.

Exposure mappingMap indicators from this story to your assets and identify affected systems in minutes.
Threat actor evidenceEvery observed campaign, victim, and pivot linked to actors named in this story.
Associated malwareMalware, exploits, and IOCs connected to the activity described here.
Detection signaturesYARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Scheduled alertsGet matching new stories delivered to your team as they break, not the next morning.
AI threadsAsk questions about this story and take action on the answers.