We use these services and cookies to improve your user experience. You may opt out if you wish, however, this may limit some features on this site.

Please see our statement on Data Privacy.

Crisp.chat (Helpdesk and Chat)

Ok

THREATINT
PUBLISHED

CVE-2025-6920

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



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.

Reserved 2025-06-30 | Published 2025-07-01 | Updated 2025-07-01 | Assigner redhat


MEDIUM: 5.3CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N

Problem types

Missing Authentication for Critical Function

Product status

Default status
affected

Default status
affected

Timeline

2025-06-30:Reported to Red Hat.
2025-06-30:Made public.

References

access.redhat.com/security/cve/CVE-2025-6920 vdb-entry

bugzilla.redhat.com/show_bug.cgi?id=2375522 (RHBZ#2375522) issue-tracking

cve.org (CVE-2025-6920)

nvd.nist.gov (CVE-2025-6920)

Download JSON

Share this page
https://cve.threatint.eu/CVE/CVE-2025-6920

Support options

Helpdesk Chat, Email, Knowledgebase