CVE-2025-6920
Last modified
CVE-2025-6920 is a medium-severity vulnerability rated 5.3/10 on the CVSS scale. 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. EPSS estimates a 0.27% chance of exploitation in the next 30 days.
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.
Metrics
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
Weakness Enumeration
Affected Software
| Vendor | Product | Versions |
|---|---|---|
| Redhat | Ai Inference Server | All versions |
References
- https://access.redhat.com/security/cve/CVE-2025-6920Vendor Advisory
- https://bugzilla.redhat.com/show_bug.cgi?id=2375522Issue Tracking, Vendor Advisory
Timeline
- Published
- Last Modified
- Status
- Analyzed
Frequently Asked Questions
What is CVE-2025-6920?
How severe is CVE-2025-6920?
How do I fix CVE-2025-6920?
Are you affected by CVE-2025-6920?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST
