# Mlflow: Command Injection when serving models with enable_mlserver=True

Advisory record · `GHSA-rvhj-8chj-8v3c`

- **Identifiers:** `GHSA-rvhj-8chj-8v3c` · `BIT-mlflow-2026-0596` · `CVE-2026-0596` · `PYSEC-2026-424`
- **State:** Confirmed
- **Severity:** CVSS 9.6 Critical
- **Critical:** Yes: CVSS 9+
- **Weakness (CWE):** [CWE-78](https://cwe.mitre.org/data/definitions/78.html)
- **Tags:** [Command injection](https://agentprime.io/advisories/tag/command-injection.md)
- **Published:** 29 Jun 2026
- **Updated:** 1 Jul 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 29 Jun 2026, 11:50 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Critical

Critical, because:

- CVSS score 9.6: 9.0 or more.

How we decide what’s critical: <https://agentprime.io/advisories/critical.md>

## Affected packages

- `mlflow` (PyPI): affected `<3.9.0`; fixed in `3.9.0`

## Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

> Mlflow versions before 3.9.0 are vulnerable to command injection when serving a model with enable_mlserver=True. The model_uri is placed unsanitized into a shell command, so an attacker who can supply a crafted model_uri can run arbitrary commands, and privilege escalation is possible if a higher-privileged service serves models from a directory that lower-privileged users can write to. Upgrade to Mlflow 3.9.0 or later.

Written 10 Nov 2026.

## Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

## Severity and exploitation

- 9.6 Critical, CVSS 3.0: `CVSS:3.0/AV:A/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H`, from CNA (@huntr_ai)

- **CISA KEV:** Not listed.
- **EPSS:** 0.014, the 72nd percentile, on 14 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

This record came from the full history of the GitHub Advisory Database, published 29 Jun 2026. New records show when each source confirmed them.

## Sources

- [GitHub Advisory Database: GHSA-rvhj-8chj-8v3c](https://github.com/advisories/GHSA-rvhj-8chj-8v3c)
- [OSV: GHSA-rvhj-8chj-8v3c](https://osv.dev/vulnerability/GHSA-rvhj-8chj-8v3c)
- <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://huntr.com/bounties/2e905add-f9f5-4309-a3db-b17de5981285>
- <https://pypi.org/project/mlflow>
- <https://github.com/advisories/GHSA-rvhj-8chj-8v3c>

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.

## Check whether this affects you

A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet.

- With the agentprime MCP server (<https://api.agentprime.io/mcp>), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: <https://agentprime.io/mcp.md>
- In a browser: <https://agentprime.io/check/> reads your lockfile in the browser, never uploading it.
- Whether it touches your code, with file and line: the Claude Code plugin, <https://agentprime.io/plugin.md>
- As JSON: <https://api.agentprime.io/v1/advisories/GHSA-rvhj-8chj-8v3c>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-rvhj-8chj-8v3c/>. Everything for agents: <https://agentprime.io/llms.txt>.