Skip to content
MediumNews

Amazon Uncovers AI Agent Campaign Targeting LiteLLM, Dify, and Other Apps for API Keys

Published
Record updated
View JSON

Summary

Amazon's threat intelligence team, using decoy servers in its MadPot network, captured records of AI agents hunting internet-exposed AI apps such as LiteLLM, One API and Dify to steal stored AI provider keys, then using those keys to run the models behind the search. The team cannot verify the reported outcomes and assesses with moderate confidence that the operators were separate China-linked groups running the open-source ARTEX penetration testing tool. The playbook targets default credentials, an authentication bypass via the isCliRequest header in One API family systems, and SSRF to cloud metadata services.