Analytical use of cookies
CVE-2026-64849: MLflow Server-Side Request Forgery Vulnerability
CVE-2026-64849: critical vulnerability affecting MLflow. Check CVSS, KEV status, business impact and recommended administrator actions.
- CVSS
- 9.3 CRITICAL
- EPSS
- 96.79%
- Known exploited
- yes
- Product
- MLflow
What is known
MLflow is an open source AI engineering platform for agents, large language models, and machine learning models. Prior to 3.15.0, the unauthenticated POST /api/2.0/mlflow/webhooks/{id}/test endpoint calls _validate_webhook_url() in mlflow/utils/validation.py only for the original URL while mlflow/webhooks/delivery.py follows redirects and re-resolves the hostname without pinning the validated address, allowing attackers to reach internal or cloud metadata services and receive response_status and response_body. This issue is fixed in version 3.15.0.
Business impact
Successful exploitation of CVE-2026-64849, a critical vulnerability (CVSS 9.3) affecting MLflow, may affect the confidentiality, integrity or availability of the vulnerable environment. The exact impact depends on the installed version, exposed interfaces and deployment configuration. CISA lists this vulnerability in the Known Exploited Vulnerabilities catalog, so exposed systems should be treated as a priority.
Recommended administrator action
Confirm whether MLflow is present and compare installed versions with the vendor advisory and NVD record. Apply the vendor patch or documented mitigation; until remediation is complete, reduce exposure of affected interfaces, review relevant logs and monitor for indicators of exploitation. Where applicable, include the CISA KEV remediation due date of 2026-09-02 in the change plan. DataHouse can support version verification, managed patching, network exposure reduction, log review and backup validation for dedicated, cloud and colocated environments.