---
title: "CVE-2026-0596: Mlflow: Command Injection when serving models with enable_mlserver=True"
url: https://erroneo.us/security/cve/CVE-2026-0596/
description: "CVE-2026-0596 (mlflow (PyPI)): A command injection vulnerability exists in mlflow/mlflow when serving a model with enablemlserver=True. The modeluri is…"
type: vulnerability-record
section: "Security Digest"
date_published: 2026-03-31
date_modified: 2026-05-20
publisher: erroneo.us
author: erroneo.us Security Desk
cve: "CVE-2026-0596"
kev: false
cvss: 9.6
epss: 0.01328
license: All rights reserved. Quote with attribution and a link.
---

# CVE-2026-0596: Mlflow: Command Injection when serving models with enable_mlserver=True

**Signal:** Critical, preconditions apply. Severe if exploited, but exploitation needs conditions that may not apply to you. (Computed from CISA KEV, EPSS and CVSS; not an editorial verdict.)

## Should you act?

- Not in CISA KEV , but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
- EPSS 1.3% , percentile 71: FIRST’s model estimates a 1.3% chance of exploitation activity in the next 30 days, higher than 71% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
- Only applies if your dependency tree includes mlflow (PyPI) < 3.9.0, fixed in 3.9.0 . Check your lockfile, including transitive dependencies.

## What it is

A command injection vulnerability exists in mlflow/mlflow when serving a model with enablemlserver=True. The modeluri is embedded directly into a shell command executed via bash -c without proper sanitization. If the modeluri 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

- PyPI `mlflow` < 3.9.0 → fixed: 3.9.0

## Affected products (CVE record)

- mlflow mlflow/mlflow: unspecified <= latest

## Severity

- @huntr_ai CVSS 3.0: 9.6 `CVSS:3.0/AV:A/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H`
- GitHub CVSS 3.1: 9.6 `CVSS:3.0/AV:A/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H`

## Exploitation

- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation poc , automatable no , technical impact total .
- FIRST EPSS (model of 2026-10-21): 1.33% probability of exploitation activity in the next 30 days; percentile 71.

## Sources

- [GitHub Advisory GHSA-rvhj-8chj-8v3c](https://github.com/advisories/GHSA-rvhj-8chj-8v3c)
- [CVE.org record CVE-2026-0596](https://www.cve.org/CVERecord?id=CVE-2026-0596)
- [NVD entry CVE-2026-0596](https://nvd.nist.gov/vuln/detail/CVE-2026-0596)
- [huntr.com](https://huntr.com/bounties/2e905add-f9f5-4309-a3db-b17de5981285)
- [github.com](https://github.com/mlflow/mlflow/pull/19738)
- [github.com](https://github.com/mlflow/mlflow/commit/202fac4c83ccc8544c087c142b80196d0e60695c)

---
Source page: https://erroneo.us/security/cve/CVE-2026-0596/ · Security Digest: https://erroneo.us/security/ · More: https://erroneo.us/llms.txt