CrowdStrike Uncovers New Agentic AI Campaigns

Summary

CrowdStrike's Counter Adversary Operations team reports on four previously unreported threat actors who left their offensive agent frameworks exposed via open directories. Between May and August 2026, CrowdStrike Intelligence documented incidents in which threat actors used AI agents that make decisions and execute commands in campaigns against healthcare, government and private-sector targets in Argentina, Brazil, the U.S., Indonesia, Russia and Kyrgyzstan.

Topics

• AI agents

Related items

• MediumCARLIY0S: CyberCartel's AI Attacks on Latin American BanksSame vendor · Straiker Blog
• Info‘Context Bombs’ Cut AI Attack Success by Misleading Agents With Fake TargetsSame vendor · SecurityWeek
• InfoNew prize launches for books co-written with AISame vendor · The Guardian Technology
• MediumAI Guardrails Aren’t Stopping Criminal HackersSame vendor · Wired (Security)
• MediumLiteLLM PyPI Package and Docker Images Compromised to Steal Cloud and AI CredentialsSame vendor · Socket Blog