CVE-2026-0596

HIGH LAB

Command Injection in mlflow/mlflow

Title source: cna
STIX 2.1

Exploitation Summary

EIP tracks 1 public exploit for CVE-2026-0596. PoCs published by SparshBiswas-AI.

AI-analyzed exploit summary This repository contains a functional exploit PoC for CVE-2026-0596, demonstrating arbitrary code execution via insecure deserialization in MLflow and MLServer. The exploit leverages Python's pickle deserialization to execute commands during model loading.

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.

Exploits (1)

github WORKING POC
by SparshBiswas-AI · pythonpoc
https://github.com/SparshBiswas-AI/CVE-2026-0596-Reproduction

This repository contains a functional exploit PoC for CVE-2026-0596, demonstrating arbitrary code execution via insecure deserialization in MLflow and MLServer. The exploit leverages Python's pickle deserialization to execute commands during model loading.

Classification
Working Poc 95%
Attack Type
Rce
Complexity
Moderate
Reliability
Reliable
Target: MLflow 2.11.1 and MLServer 1.3.5
No auth needed
Prerequisites: Docker environment · MLflow and MLServer installed
devstral-2 · analyzed May 18, 2026 Full analysis →

Scores

CVSS v3 7.8
EPSS 0.0133
EPSS Percentile 67.2%
Attack Vector LOCAL
CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

CISA SSVC

Vulnrichment
Exploitation poc
Automatable no
Technical Impact total

Details

CWE
CWE-78
Status published
Products (4)
lfprojects/mlflow
mlflow/mlflow/mlflow unspecified - latest
pypi/mflow 0 - 3.9.0PyPI
pypi/mlflow 0 - 3.9.0PyPI
Published Mar 31, 2026
Tracked Since Mar 31, 2026