{"id":7469,"date":"2025-07-01T09:47:22","date_gmt":"2025-07-01T09:47:22","guid":{"rendered":"http:\/\/localhost\/?p=7469"},"modified":"2025-07-01T09:47:22","modified_gmt":"2025-07-01T09:47:22","slug":"ai-inference-server-authentication-bypass-via-unprotected-inference-endpoint-in-api","status":"publish","type":"post","link":"https:\/\/zero.redgem.net\/?p=7469","title":{"rendered":"Ai-inference-server: authentication bypass via unprotected inference endpoint in api"},"content":{"rendered":"
\n

CVE Details<\/h2>\n
\n
\n

Basic Information<\/h3>\n\n\n\n\n\n
Title<\/th>\nAi-inference-server: authentication bypass via unprotected inference endpoint in api<\/td>\n<\/tr>\n
Type<\/th>\ncve<\/td>\n<\/tr>\n
Published<\/th>\n2025-07-01T13:16:17.180Z<\/td>\n<\/tr>\n
Modified<\/th>\n2025-07-01T13:30:18.432Z<\/td>\n<\/tr>\n<\/table>\n<\/div>\n
\n

Product Information<\/h3>\n\n\n\n
Vendor<\/th>\nRed Hat<\/td>\n<\/tr>\n
Product<\/th>\nRed Hat AI Inference Server<\/td>\n<\/tr>\n<\/table>\n<\/div>\n<\/div>\n
\n

CVSS Information<\/h3>\n\n\n\n
Base Score<\/th>\n5.3 (MEDIUM)<\/td>\n<\/tr>\n
Attack Vector<\/th>\nCVSS:3.1\/AV:N\/AC:L\/PR:N\/UI:N\/S:U\/C:L\/I:N\/A:N<\/td>\n<\/tr>\n<\/table>\n<\/div>\n
\n

AI Analysis<\/h3>\n\n\n\n\n\n
AI Description<\/th>\nA vulnerability in Red Hat AI Inference Server allows unauthorized access to API endpoints due to missing authentication checks, potentially exposing sensitive data or functionality.<\/td>\n<\/tr>\n
AI Severity<\/th>\nHigh<\/td>\n<\/tr>\n
AI Vendor<\/th>\nRed Hat<\/td>\n<\/tr>\n
AI Product<\/th>\nRed Hat AI Inference Server<\/td>\n<\/tr>\n<\/table>\n<\/div>\n
\n

Additional Information<\/h3>\n\n\n\n
CWE List<\/th>\nCWE-306<\/td>\n<\/tr>\n
Source<\/th>\nredhat<\/td>\n<\/tr>\n<\/table>\n<\/div>\n
\n

Description<\/h3>\n
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.<\/div>\n<\/div>\n
\n

References<\/h4>\n