Skip to content
Amazon Exposes AI Campaign Targeting API Keys with ARTEX Framework

Amazon Exposes AI Campaign Targeting API Keys with ARTEX Framework

First seen 16 Nov 2026, 09:16 UTC • •

Article Content

Browse articles
ThreatCluster AI
ThreatCluster •November 16, 2026 at 11:44 UTC
  • •AI agents used ARTEX to steal API keys from exposed applications.
  • •The campaign targeted multiple AI platforms, including LiteLLM and Dify.
  • •Amazon captured operational records via its MadPot decoy network.

Amazon's threat intelligence team revealed a campaign where AI agents used the ARTEX framework to steal API keys from various AI applications, including LiteLLM and Dify. The attacks occurred between October 3 and November 5, 2026, with the agents targeting internet-exposed applications to extract provider keys. These stolen keys were then utilized to power further credential theft operations, creating a self-sustaining cycle. Amazon captured the agents' operational records through its MadPot decoy network, which posed as popular LLM APIs. The attackers, believed to be linked to multiple groups in China, used prompts in Simplified Chinese and avoided targeting mainland China. The campaign exploited known vulnerabilities, including CVE-2025-3248 and CVE-2026-28797, and focused on applications that store multiple provider keys, making them particularly vulnerable. Amazon has not confirmed the success of the attacks but assessed the threat with moderate confidence.

Start a free Starter trial for enhanced analysis

Ask AI about this cluster

Timeline

2025-04-07
CVE-2025-3248 published
A critical remote code execution vulnerability was published, affecting various applications.
Gbhackers
2026-04-03
CVE-2026-28797 published
A high-severity vulnerability was published, impacting systems used by the ARTEX agents.
Gbhackers
2026-11-12
CVE-2026-123039 published
A high-severity vulnerability was published and added to CISA's KEV list.
aws.amazon.com
Recent
Amazon reports ARTEX campaign
Amazon disclosed findings of an AI-driven credential theft campaign using ARTEX.
Securityaffairs

More articles in this cluster (8)

Following this threat?

Track blacknevas, Amazon and CVE-2025-3248 in your own feed — you're alerted when they show up in new reporting, leak sites or exploitation.

Free account · no card needed

Common questions

Which applications are affected?
The campaign targeted applications like LiteLLM, Dify, and various API gateways.
What vulnerabilities are involved?
Notable vulnerabilities include CVE-2025-3248 and CVE-2026-28797, which were exploited during the campaign.
How can we protect against this threat?
Review security configurations for exposed applications and apply relevant patches for known vulnerabilities.