Inside the loop: Five AI attack frameworks that never ask permission

Summary

Five agentic offensive frameworks, ARTEX, CyberStrikeAI, Cairn, PentAGI, and HexStrike, have drawn more than 60,000 GitHub stars and have already appeared in intrusions. Google Threat Intelligence Group and Mandiant observed ARTEX, Cairn, HexStrike, and PentAGI in incident response engagements, and Microsoft attributed ARTEX use to Storm-0940. None of the five enforces authorization in code, and ARTEX's execution bursts last roughly two to 25 seconds.

Related items

• MediumARTEX and beyond: AI-enabled penetration testing platformsSimilar attack · Cisco Talos Blog
• InfoHow AI is changing the nature of cyberattacksSimilar attack · CSO Online
• MediumARTEX: Attackers Adopted This AI Pentesting Tool in Three Months. Leaked Secrets Are Its Fastest Way In.Similar attack · StepSecurity Blog
• MediumFBI Says North Korean Hackers Stole Over $400 Million in Crypto Using Deepfake Video CallsSimilar attack · The Hacker News
• MediumCVE-2026-126395: vLLM information disclosure via uppercase PIL image addresses in error messagesSimilar attack · NVD/CVE Database