CVE-2025-6920 - CVE House

Back to Database

Status published Medium CVE-2025-6920

Ai-inference-server: authentication bypass via unprotected inference endpoint in api

5.3 CVSS

Vulnerability Description

A flaw was found in the authentication enforcement mechanism of a model inference API in ai-inference-server. All /v1/* endpoints are expected to enforce API key validation. However, the POST /invocations endpoint failed to do so, resulting in an authentication bypass. This vulnerability allows unauthorized users to access the same inference features available on protected endpoints, potentially exposing sensitive functionality or allowing unintended access to backend resources.

Impact Analysis

Refer to official advisory for detailed impact metrics.

Remediation

Ensure systems are updated to the latest vendor-supplied patch levels.

THREAT MONITOR

Am I Vulnerable?

Launch our assessment wizard to check if your infrastructure is exposed to • CVE-2025-6920

Check My Exposure

Credits & Attribution

No credits recorded in the NVD database.

References

More from Red Hat

View All →

Aap-gateway: improper path validation in gateway allows credential exfiltration

Event-driven-ansible: sensitive internal headers disclosure in aap eda event streams

Event-driven-ansible: event stream test mode exposes sensitive headers in aap eda

Libsoup: improper handling of http vary header in libsoup caching

Gnutls: stack-based buffer overflow in gnutls_pkcs11_token_init() function

Affected Vendor

Red Hat

View all reports →

Affected Software

Red Hat AI Inference Server

Vulnerable Versions:

Unknown

Timeline

Official Publish: July 1st, 2025

Last Modified: November 20th, 2025

Added to House: July 22nd, 2026

CVSS Vectors

V3: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N

Weaknesses (CWE)

MITRE ATT&CK TTPs

T1190 Exploit Public-Facing Application

T1078 Valid Accounts

T1136 Create Account

T1098 Account Manipulation

Privilege Escalation

T1021 Remote Services

Lateral Movement