Vulnerability record · CVE-2025-6920 · published 1 July 2025
CVE-2025-6920: Redhat ai inference server missing authentication for critical function vulnerability
Redhat · Ai Inference Server
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.
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.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
Affected products
1 vulnerable configurations from NVD's CPE data, grouped by vendor and product.
References
| Link | Tags |
|---|---|
| https://access.redhat.com/security/cve/CVE-2025-6920 | Vendor Advisory |
| https://bugzilla.redhat.com/show_bug.cgi?id=2375522 | Issue TrackingVendor Advisory |
Track CVE-2025-6920 inside VULONE
Watch it alongside the ransomware crews, C2 infrastructure and forum chatter that reference it, query it through the API and pull it into your SIEM over TAXII.
Related vulnerabilities
Same products first, then exploited flaws of the same weakness class.
Source: NIST National Vulnerability Database (record CVE-2025-6920), CISA KEV, FIRST EPSS (scores of 2026-10-01). This page is refreshed as NVD updates the record.
