Auth bypass in Red Hat Ai Inference Server
CVE-2025-6920
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.
Vulnerability class: Broken Authentication
EPSS: 0.003 (18.8th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 5.3 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N.
Affected products
Weakness classification (CWE)
References
- secalert@redhat.com (x_refsource_REDHAT, vdb-entry, Vendor Advisory)
- secalert@redhat.com (x_refsource_REDHAT, issue-tracking, Issue Tracking, Vendor Advisory)
Frequently asked questions
- What is CVE-2025-6920?
- CVE-2025-6920 is a medium-severity vulnerability in Red Hat Ai Inference Server, classified under Missing Authentication for Critical Function. CVSS score: 5.3/10. Published 2025-07-01.
- How severe is CVE-2025-6920?
- Medium severity. CVSS v3 base score is 5.3 out of 10.