CVE-2026-0596

A command injection vulnerability exists in mlflow/mlflow when serving a model with `enable_mlserver=True`. The `model_uri` is embedded directly into a shell command executed via `bash -c` without proper sanitization. If the `model_uri` contains shell metacharacters, such as `$()` or backticks, it allows for command substitution and execution of attacker-controlled commands. This vulnerability affects the latest version of mlflow/mlflow and can lead to privilege escalation if a higher-privileged service serves models from a directory writable by lower-privileged users.

Affected products

Mlflow

Lfprojects Mlflow

All versions

CVSS 3.0

9.6 CRITICAL

EPSS

1.3% (68th percentile)

Weakness

CWE-78

NVD status

Analyzed

Published

2026-03-31