Browse / AI Framework and Platform Flaws / CVE-2026-0596
Mlflow: Command Injection when serving models with enable_mlserver=True
- Class
- AI Framework and Platform Flaws (filed by a model that read the advisory)
- Technique
- Code and command execution
- Affected
- mlflow (PyPI)
- CVSS
- CVSS:3.0/AV:A/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
- EPSS
- 1.4% chance of exploitation in 30 days
How it works, in short
The model URI is interpolated unescaped into a bash -c command, so shell command substitutions inside it run when the model is served. (Our summary, written by a model. The source text is below.)
Details
A command injection vulnerability exists in 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.
References
- https://nvd.nist.gov/vuln/detail/CVE-2026-0596
- https://github.com/mlflow/mlflow/pull/19738
- https://github.com/mlflow/mlflow/commit/202fac4c83ccc8544c087c142b80196d0e60695c
- https://github.com/mlflow/mlflow
- https://github.com/pypa/advisory-database/tree/main/vulns/mlflow/PYSEC-2026-424.yaml
- https://huntr.com/bounties/2e905add-f9f5-4309-a3db-b17de5981285
- https://pypi.org/project/mlflow
Source: GitHub Advisory Database, used under CC BY 4.0.