VYPR
High severity7.8NVD Advisory· Published Mar 31, 2026· Updated Apr 14, 2026

CVE-2026-0596

CVE-2026-0596

Description

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 packages

Versions sourced from the GitHub Security Advisory.

PackageAffected versionsPatched versions
mflowPyPI
< 3.9.03.9.0

Affected products

1

Patches

1
202fac4c83cc

Fix Command Injection in model serving (#19738)

https://github.com/mlflow/mlflowWeichenXuJan 5, 2026via ghsa
1 file changed · +2 1
  • mlflow/pyfunc/mlserver.py+2 1 modified
    @@ -1,5 +1,6 @@
     import logging
     import os
    +import shlex
     
     _logger = logging.getLogger(__name__)
     
    @@ -16,7 +17,7 @@ def get_cmd(
         model_name: str | None = None,
         model_version: str | None = None,
     ) -> tuple[str, dict[str, str]]:
    -    cmd = f"mlserver start {model_uri}"
    +    cmd = f"mlserver start {shlex.quote(model_uri)}"
     
         cmd_env = os.environ.copy()
     
    

Vulnerability mechanics

Generated by null/stub on May 9, 2026. Inputs: CWE entries + fix-commit diffs from this CVE's patches. Citations validated against bundle.

References

5

News mentions

0

No linked articles in our index yet.