# CVE-2026-0596: MLflow command injection in model serving via model_uri

Source: https://junglewise.ai/threats/cve-2026-0596-mlflow-command-injection-in-model-serving-via-model-uri  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-03-31. Updated: 2026-07-21  
License: CC BY 4.0 with a link back

CVE-2026-0596 · Severity: critical · CVSS 9.6 · Published 2026-03-31

MLflow, a popular platform for managing machine learning lifecycles, contains a security flaw in its model serving component. An attacker can execute unauthorized commands on the server by providing a specially crafted model location. This could allow a low-privileged user to take full control of the machine learning server or access sensitive data.

Technologies: [mlflow (PyPI)](https://junglewise.ai/threats/technologies/mlflow). Vendors: [PyPI](https://junglewise.ai/threats/vendors/pypi).

## Quick answers

**Is CVE-2026-0596 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-0596 being exploited in the wild.

**How severe is CVE-2026-0596?** Critical severity, with a CVSS score of 9.6, published 31 March 2026.

**Which products and versions are affected?** mlflow (PyPI) < 3.9.0, ECOSYSTEM:introduced=0,fixed=3.9.0.

**Is there a fix for CVE-2026-0596?** Yes. mlflow (PyPI): upgrade to 3.9.0 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-0596 attacked?** It is attacked with local access or from the adjacent network, in a software library.

**Am I affected by CVE-2026-0596?** Check whether you run mlflow (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- mlflow (PyPI): upgrade to 3.9.0 or later

  ```sh
  pip install "mlflow>=3.9.0"
  ```


## Technical details

A command injection vulnerability (CWE-78) exists in MLflow when the `enable_mlserver=True` flag is used during model serving. The root cause is the lack of sanitization for the `model_uri` parameter, which is directly embedded into a shell command executed via `bash -c`. An attacker can use shell metacharacters like backticks or `$()` within the `model_uri` to achieve command substitution. This can be exploited locally or via an adjacent network depending on the deployment, potentially leading to privilege escalation if a high-privileged service processes models from directories writable by lower-privileged users. At the time of the advisory, the vulnerability was reported to affect the latest version of MLflow.

## Affected products

- mlflow mlflow latest

## Identifiers

- CVE-2026-0596
- GHSA-rvhj-8chj-8v3c
- PYSEC-2026-424

## Timeline

- 2026-03-31: disclosed
- 2026-03-31: advisory

## References

- [https://huntr.com/bounties/2e905add-f9f5-4309-a3db-b17de5981285](https://huntr.com/bounties/2e905add-f9f5-4309-a3db-b17de5981285)

## Related threats

- [MLflow arbitrary code execution in third-party scorer deserialization](https://junglewise.ai/threats/cve-2026-116692-mlflow-is-an-open-source-ai-engineering-platform-for-agents)
- [MLflow credential leak in CrewAI autolog](https://junglewise.ai/threats/cve-2026-116691-mlflow-is-an-open-source-ai-engineering-platform-for-agents)
- [MLflow path traversal in prompt model version artifact access](https://junglewise.ai/threats/cve-2026-116690-mlflow-is-an-open-source-ai-engineering-platform-for-agents)
- [MLflow unsafe deserialization in scorer endpoints](https://junglewise.ai/threats/cve-2026-115886-mlflow-is-an-open-source-ai-engineering-platform-for-agents)
- [MLflow FileStore path traversal in trace storage](https://junglewise.ai/threats/cve-2026-53995-mlflow-3-17-1-and-earlier-contains-a-path-traversal-vulnerability)