MLflow AI Gateway SSRF can leak data if authenticated (CVE-2026-71211)
Original title: ZDI-26-847: MLflow AI Gateway Server-Side Request Forgery Information Disclosure Vulnerability
ZDI rates the authenticated flaw 7.7; the snippet does not name versions or a patch.
ZDI published ZDI-26-847 for an MLflow AI Gateway server-side request forgery issue described as an information-disclosure vulnerability. Authenticated remote attackers can initiate arbitrary server-side requests. ZDI assigned CVSS 7.7 and CVE-2026-71211. Versions, fixes, and exploitation are not stated.
Unconfirmed: Affected versions, a fix, and whether attackers exploit it are not stated.
- Authentication is required to exploit the AI Gateway flaw.
- The title classifies it as SSRF information disclosure.
- ZDI assigned a CVSS rating of 7.7.
- The advisory id is ZDI-26-847 and the CVE is CVE-2026-71211.
Impact: Authenticated arbitrary server-side requests and information disclosure
| Product | Affected |
|---|---|
| MLflow AI Gateway | — |
- CVEs
- CVE-2026-71211
- Products
- MLflowMLflow AI Gateway
- Organizations
- Zero Day Initiative
Vulnerabilities mentioned
All| CVE | Vulnerability | CVSS | EPSS | Signals | Published |
|---|---|---|---|---|---|
| CVE-2026-71211 | MLflow's AI Gateway accepts an auth_config.api_base value when creating a gateway secret (mlflow/server/handlers.py, _create_gateway_secret) with no validation… | 7.1 | <1% |
From the original article
This vulnerability allows remote attackers to initiate arbitrary server-side requests on affected installations of MLflow. Authentication is required to exploit this vulnerability. The ZDI has assigned a CVSS rating of 7.
zerodayinitiative.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.