logo

Chinese Hackers Exploit Stolen LLM API Keys for Credential Theft via ARTEX

ID: 2eee2924-f560-5a82-a17f-71c423657776

STIX ID: report--2eee2924-f560-5a82-a17f-71c423657776

Feed Name: ThreatCluster

Threat Score
78/100

Date Published: 2026-11-14

Date Updated: 2026-11-15

...
...

Amazon Threat Intelligence observed Chinese-nexus actors (assessed with moderate confidence) using the ARTEX penetration-testing framework between Oct 3 and Nov 5, 2026 to exploit stolen LLM API keys and exfiltrate credentials from AI gateways (e.g., One API, LiteLLM) and management interfaces, leveraging known vulnerabilities CVE-2025-3248 and CVE-2026-28797, searching client-side JavaScript for secrets, and operating a self-sustaining inference loop to monetize stolen keys; a separate campaign used deepfakes to bypass cryptocurrency exchange KYC checks.

Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.