Agentic AI Attacks Are Here: What We're Seeing with ARTEX, and How to Protect Your Org
Salesforce, Thursday, November 12th, 2026
Salesforce Threat Intelligence reports threat actors using the ARTEX agentic attack framework against Salesforce environments.
Salesforce Threat Intelligence has observed multiple threat actors using ARTEX, an open-source multi-agent offensive framework originally built for autonomous penetration testing, to try to access Salesforce environments.
The original GitHub repository was taken down by its creator but forks still circulate, and Salesforce assesses it as a capability accessible to many actors.
Microsoft has attributed ARTEX campaigns to the China-aligned Storm-0940 and the financially motivated Storm-3358.
Salesforce saw a stolen-credential campaign using compromised application credentials and trusted integration sessions, not a platform vulnerability, with tactics such as relaying requests through Apex, deploying custom code and testing permissions.