CVE-2026-64849

Aliases:GHSA-7gwp-5pfp-969j
Received
Published: 17 Aug 2026, 21:16
Last modified:17 Aug 2026, 21:16

Vulnerability Summary

Overall Risk (default)
high
70/100
CVSS Score
9.3 CRITICAL
v3.1 (cve.org)
EPSS Score
No data
KEV
Not listed
Ransomware
No reports
Public exploits
None found
Dark Web
Not detected

Timeline

17 Aug 2026, 21:16
Published
Vulnerability first disclosed

Description

MLflow is an open source AI engineering platform for agents, large language models, and machine learning models. Prior to 3.15.0, the unauthenticated POST /api/2.0/mlflow/webhooks/{id}/test endpoint calls _validate_webhook_url() in mlflow/utils/validation.py only for the original URL while mlflow/webhooks/delivery.py follows redirects and re-resolves the hostname without pinning the validated address, allowing attackers to reach internal or cloud metadata services and receive response_status and response_body. This issue is fixed in version 3.15.0.

CVSS Metrics

  • v3.1•CRITICAL•Score: 9.3CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N

Techniques & Countermeasures

  • CWE-918•Server-Side Request Forgery (SSRF)

    The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination.

Affected Systems

  • mlflow•mlflow

    < 3.15.0

  • PyPI•mlflow

    < 3.15.0

References (6)