Amazon finds hackers running ARTEX AI agents to steal AI model keys

Nov 16, 2026
Decoy sensors captured the agents' memory: stolen keys from apps like LiteLLM and Dify paid for the AI hunting for more keys.

Amazon's threat intelligence team says threat actors have been running cybercrime campaigns with ARTEX, an open-source agentic AI penetration testing framework, including a large-scale theft of credentials for AI models, according to an AWS security blog post. From October 3 to November 5, Amazon's MadPot decoy sensors captured requests from AI agents that contained the operating memory of these campaigns.

In the most prominent campaign, the agents found internet-exposed AI applications that store provider keys, such as LiteLLM, One API and Dify, extracted and validated the keys, and fed them into the framework's own model gateway, so stolen keys paid for the AI powering the search for more keys. Another campaign targeted cryptocurrency exchanges with real-time deepfake injection to bypass identity checks.

Amazon assesses with moderate confidence that ARTEX was used and that the activity comes from disparate Chinese-nexus groups, citing simplified Chinese prompts and China time-zone settings. It says it cannot verify the outcomes the agents reported, and has notified potentially affected customers and published indicators of compromise, The Hacker News reports.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Cybersecurity AI Weekly or Daily AI Brief.

Also, consider following us on social media:

Free newsletter

Cybersecurity AI Weekly

Weekly newsletter about AI in Cybersecurity.

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.