NVIDIA Triton Inference Server MLflow plugin path traversal

Summaryinfo

A vulnerability classified as very critical has been found in NVIDIA Triton Inference Server. The impacted element is an unknown function of the component MLflow plugin. This manipulation causes path traversal. The identification of this vulnerability is CVE-2026-47487. It is possible to initiate the attack remotely. There is no exploit available.

Detailsinfo

A vulnerability was found in NVIDIA Triton Inference Server (version now known). It has been declared as very critical. Affected by this vulnerability is some unknown processing of the component MLflow plugin. The manipulation with an unknown input leads to a path traversal vulnerability. The CWE definition for the vulnerability is CWE-22. The product uses external input to construct a pathname that is intended to identify a file or directory that is located underneath a restricted parent directory, but the product does not properly neutralize special elements within the pathname that can cause the pathname to resolve to a location that is outside of the restricted directory. As an impact it is known to affect confidentiality, integrity, and availability. The summary by CVE is:

NVIDIA Triton Inference Server for Linux contains a vulnerability where a user could cause files outside the model repository to be read, written to, or modified by providing a path in the model name to the Triton MLflow plugin. A successful exploit of this vulnerability might lead to denial of service and information disclosure.

This vulnerability is known as CVE-2026-47487 since 05/19/2026. The exploitation appears to be easy. The attack can be launched remotely. Neither technical details nor an exploit are publicly available. The price for an exploit might be around USD $0-$5k at the moment (estimation calculated on 08/04/2026). MITRE ATT&CK project uses the attack technique T1006 for this issue.

There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.

If you want to get the best quality for vulnerability data then you always have to consider VulDB.

Productinfo

Vendor

• NVIDIA

Name

• Triton Inference Server

License

• commercial

Website

• Vendor: https://www.nvidia.com/

CPE 2.3info

• 🔒

CPE 2.2info

• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

If you want to get the best quality for vulnerability data then you always have to consider VulDB.

Discussion