- 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.
- Source
- secalert@redhat.com
- NVD status
- Awaiting Analysis
CVSS 3.1
- Type
- Primary
- Base score
- 5.3
- Impact score
- 1.4
- Exploitability score
- 3.9
- Vector string
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
- Severity
- MEDIUM
- secalert@redhat.com
- CWE-306
- Hype score
- Not currently trending
CVE-2025-6920 Authentication Bypass in AI Inference Server API via Unvalidated /invocations Endpoint https://t.co/UM1GAlzq4G
@VulmonFeeds
1 Jul 2025
1 Impression
0 Retweets
0 Likes
0 Bookmarks
0 Replies
0 Quotes
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 valida… https://t.co/iZBK4KLEoU
@CVEnew
1 Jul 2025
341 Impressions
0 Retweets
0 Likes
0 Bookmarks
0 Replies
0 Quotes