ZDI 2026-10-29

ZDI-26-847: MLflow AI Gateway Server-Side Request Forgery Information Disclosure Vulnerability

CVE-2026-71211

Machine-generated analysis · WAYSCloud LLM

Authenticated remote attackers can trigger arbitrary server-side requests via MLflow’s AI Gateway (SSRF). The advisory assigns a CVSS score of 7.7.

Context

The advisory concerns the MLflow AI Gateway component. It describes a server-side request forgery vulnerability that allows authenticated remote attackers to initiate arbitrary server-side requests. The advisory assigns a CVSS rating of 7.7 (CVE-2026-71211).

Operator considerations

Check: Verify presence of MLflow AI Gateway deployments and confirm authentication enforcement.
Log: Enable logging of outbound requests made through the AI Gateway to detect SSRF activity.

From Zero Day Initiative ↗

This vulnerability allows remote attackers to initiate arbitrary server-side requests on affected installations of MLflow. Authentication is required to exploit this vulnerability. The ZDI has assigned a CVSS rating of 7.7. The following CVEs are assigned: CVE-2026-71211.

Read the full advisory on ZDI →