Deserialization of Untrusted Data in MLflow - CVE-2026-118627
Published: November 3, 2026
Vulnerability details
The vulnerability allows a remote attacker to execute arbitrary code on the target system.
The vulnerability exists due to insecure input validation when processing serialized data within the loading of SHAP explainer models. A remote attacker can trick a victim to open a specially crafted file or visit a malicious website and execute arbitrary code on the target system.
Successful exploitation of this vulnerability may result in complete compromise of vulnerable system.