Databricks Genie Code Malicious Skill Enables Phishing and Data Exfiltration

PromptArmor reports that a malicious Skill can make Databricks Genie Code display a phishing modal and exfiltrate tenant data without human approval.

The attack exploits Skills loaded from users' personal workspaces and a display interface that lacks egress controls, and Databricks, after disclosure on August 16, 2026, said users are responsible for ensuring uploaded Skills contain no malicious content.