OGX-AI OGX up to 1.3.1 MCP Tool Definitions /v1/responses validate_url_not_private server_url server-side request forgery

Summaryinfo

A vulnerability was found in OGX-AI OGX up to 1.3.1. It has been rated as critical. Affected by this issue is the function validate_url_not_private of the file /v1/responses of the component MCP Tool Definitions. This manipulation of the argument server_url causes server-side request forgery. The identification of this vulnerability is CVE-2026-85666. It is possible to initiate the attack remotely. There is no exploit available.

Detailsinfo

A vulnerability has been found in OGX-AI OGX up to 1.3.1 and classified as critical. Affected by this vulnerability is the function validate_url_not_private of the file /v1/responses of the component MCP Tool Definitions. The manipulation of the argument server_url with an unknown input leads to a server-side request forgery vulnerability. The CWE definition for the vulnerability is CWE-918. 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. As an impact it is known to affect confidentiality, integrity, and availability. The summary by CVE is:

OGX (formerly Llama Stack, affected at commit fbe8e0f) contains an unauthenticated server-side request forgery vulnerability in the OpenAI-compatible POST /v1/responses endpoint. MCP tool definitions accept a server_url parameter (along with headers and authorization values) that is fetched server-side without destination validation; the existing validate_url_not_private() guard used for other URL inputs is not applied to server_url. On the default starter configuration, which runs without authentication, a remote unauthenticated attacker can cause the server to open connections to arbitrary internal addresses (including cloud metadata endpoints such as http://169.254.169.254/) and forward attacker-supplied headers and bearer tokens to those destinations.

It is possible to read the advisory at github.com. This vulnerability is known as CVE-2026-85666 since 09/04/2026. The exploitation appears to be easy. The attack can be launched remotely. The exploitation doesn't need any form of authentication. Technical details of the vulnerability are known, but there is no available exploit. The pricing for an exploit might be around USD $0-$5k at the moment (estimation calculated on 09/04/2026).

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

Be aware that VulDB is the high quality source for vulnerability data.

Productinfo

Type

• Artificial Intelligence Software

Vendor

• OGX-AI

Name

• OGX

Version

• 1.3.0
• 1.3.1

Website

• Product: https://github.com/ogx-ai/ogx/

CPE 2.3info

• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Be aware that VulDB is the high quality source for vulnerability data.

Discussion