FBI issues a FLASH alert on attackers' use of the ARTEX AI penetration testing framework

FBI · Security advisory

Read the source (opens in a new tab)
What happened
The FBI released FLASH alert FLASH-20261113-001 on November 13, 2026, saying a variety of malicious actors have weaponized ARTEX, an open-source autonomous AI penetration testing framework, since at least August 2026.
Key points
  • The FBI says ARTEX lets threat actors "with minimal technical expertise" run complex, multi-target operations, with some intrusions reaching privileged access in under three hours.
  • Campaigns it names include attacks on South Korean financial institutions that took personal information of approximately 67,000 people, and a compromise of ConnectWise Cloud Backup customers that enabled access to more than 2,250 downstream tenants.
  • It says DeepSeek Flash family models dominate attacker use, citing low cost and "lack of observable guardrails when framed for penetration testing."
  • The FBI asks organizations to report ARTEX incidents to field offices or IC3 and urges organizations to inventory partner portals and other peripheral systems.
Evidence
Government alert compiling published reports by Microsoft, Google, CrowdStrike, Censys, Check Point, Zscaler, Akamai and CERT-EU, footnoted throughout, with indicators and mitigations. It cites no FBI case data of its own.

See it in the latest record