Chinese-nexus hackers use stolen LLM API keys to power ARTEX AI agents
- Severity
- High
- Sources
- 1
What happened
Chinese-nexus, financially motivated threat actors abused ARTEX, an open-source agentic penetration-testing framework, to harvest large language model API credentials and reuse them to run further attacks and credential theft. Amazon Threat Intelligence identified the campaigns via its MadPot decoy network, which captured requests containing the agents' operational memory between October 3 and November 5, 2026. The source article is truncated and cites no CVEs or affected versions. Defenders should treat LLM API keys as high-value credentials, monitor for unexpected use of them, and check for ARTEX-style agent traffic.
For security analysts · Written by AI from 1 source · Wrong?
What to do
- No action needed.
Written by AI from the sources, checked against them
Full story timeline · 1 update
Who reported · 1 outlet
Who and what is in it
Companies
Products