CVE-2025-6920
MEDIUMDescription
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.
Is your site exposed to CVE-2025-6920?
Run a free security scan — no signup, results in seconds.
CVSS v3.1 Score
Weakness Type (CWE)
Affected Products
| Vendor | Product |
|---|---|
| redhat | ai_inference_server |
References
Frequently Asked Questions
What is CVE-2025-6920? +
How severe is CVE-2025-6920? +
What products are affected by CVE-2025-6920? +
How do I check if I'm vulnerable to CVE-2025-6920? +
Related Vulnerabilities
An improper access control vulnerability in the canonical-livepatch snap client prior to version 10.15.0 allows a local unprivileged user to …
A missing authentication vulnerability exists in the Altium 365 SearchService. A legacy SOAP endpoint exposes search index operations without requiring …
Inadequate access control in the registration process in Fullstep V5, which could allow unauthenticated users to obtain a valid JWT …
A weakness in SpiceJet’s public booking retrieval page permits full passenger booking details to be accessed using only a PNR …
A Missing Authentication for Critical Function vulnerability in the GRUB configuration used B&R APROL <4.4-01 may allow an unauthenticated physical …
A security issue exists within the 1715-AENTR EtherNet/IP Adapter. The affected product exposes a network-accessible debug port that does not …