CVE-2025-6920

{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2025-6920", "assignerOrgId": "53f830b8-0a3f-465b-8143-3b8a9948e749", "state": "PUBLISHED", "assignerShortName": "redhat", "dateReserved": "2025-06-30T09:05:19.410Z", "datePublished": "2025-07-01T13:16:17.180Z", "dateUpdated": "2025-11-20T20:59:11.209Z"}, "containers": {"cna": {"title": "Ai-inference-server: authentication bypass via unprotected inference endpoint in api", "metrics": [{"other": {"content": {"value": "Moderate", "namespace": "https://access.redhat.com/security/updates/classification/"}, "type": "Red Hat severity rating"}}, {"cvssV3_1": {"attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "NONE", "baseScore": 5.3, "baseSeverity": "MEDIUM", "confidentialityImpact": "LOW", "integrityImpact": "NONE", "privilegesRequired": "NONE", "scope": "UNCHANGED", "userInteraction": "NONE", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N", "version": "3.1"}, "format": "CVSS"}], "descriptions": [{"lang": "en", "value": "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."}], "affected": [{"vendor": "Red Hat", "product": "Red Hat AI Inference Server", "collectionURL": "https://access.redhat.com/downloads/content/package-browser/", "packageName": "rhaiis/vllm-cuda-rhel9", "defaultStatus": "affected", "cpes": ["cpe:/a:redhat:ai_inference_server:3"]}, {"vendor": "Red Hat", "product": "Red Hat AI Inference Server", "collectionURL": "https://access.redhat.com/downloads/content/package-browser/", "packageName": "rhaiis/vllm-rocm-rhel9", "defaultStatus": "affected", "cpes": ["cpe:/a:redhat:ai_inference_server:3"]}], "references": [{"url": "https://access.redhat.com/security/cve/CVE-2025-6920", "tags": ["vdb-entry", "x_refsource_REDHAT"]}, {"url": "https://bugzilla.redhat.com/show_bug.cgi?id=2375522", "name": "RHBZ#2375522", "tags": ["issue-tracking", "x_refsource_REDHAT"]}], "datePublic": "2025-06-30T00:00:00.000Z", "problemTypes": [{"descriptions": [{"cweId": "CWE-306", "description": "Missing Authentication for Critical Function", "lang": "en", "type": "CWE"}]}], "x_redhatCweChain": "CWE-306: Missing Authentication for Critical Function", "workarounds": [{"lang": "en", "value": "Mitigation for this issue is either not available or the currently available options don't meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base or stability."}], "timeline": [{"lang": "en", "time": "2025-06-30T06:18:22.478Z", "value": "Reported to Red Hat."}, {"lang": "en", "time": "2025-06-30T00:00:00.000Z", "value": "Made public."}], "providerMetadata": {"orgId": "53f830b8-0a3f-465b-8143-3b8a9948e749", "shortName": "redhat", "dateUpdated": "2025-11-20T20:59:11.209Z"}}, "adp": [{"metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2025-07-01T13:30:12.685492Z", "id": "CVE-2025-6920", "options": [{"Exploitation": "none"}, {"Automatable": "yes"}, {"Technical Impact": "partial"}], "role": "CISA Coordinator", "version": "2.0.3"}}}], "title": "CISA ADP Vulnrichment", "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2025-07-01T13:30:18.432Z"}}]}}

{"dataType": "CVE_RECORD", "containers": {"adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2025-6920", "role": "CISA Coordinator", "options": [{"Exploitation": "none"}, {"Automatable": "yes"}, {"Technical Impact": "partial"}], "version": "2.0.3", "timestamp": "2025-07-01T13:30:12.685492Z"}}}], "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2025-07-01T13:30:14.637Z"}}], "cna": {"title": "Ai-inference-server: authentication bypass via unprotected inference endpoint in api", "metrics": [{"other": {"type": "Red Hat severity rating", "content": {"value": "Moderate", "namespace": "https://access.redhat.com/security/updates/classification/"}}}, {"format": "CVSS", "cvssV3_1": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 5.3, "attackVector": "NETWORK", "baseSeverity": "MEDIUM", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N", "integrityImpact": "NONE", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "NONE", "privilegesRequired": "NONE", "confidentialityImpact": "LOW"}}], "affected": [{"cpes": ["cpe:/a:redhat:ai_inference_server:3"], "vendor": "Red Hat", "product": "Red Hat AI Inference Server", "packageName": "rhaiis/vllm-cuda-rhel9", "collectionURL": "https://access.redhat.com/downloads/content/package-browser/", "defaultStatus": "affected"}, {"cpes": ["cpe:/a:redhat:ai_inference_server:3"], "vendor": "Red Hat", "product": "Red Hat AI Inference Server", "packageName": "rhaiis/vllm-rocm-rhel9", "collectionURL": "https://access.redhat.com/downloads/content/package-browser/", "defaultStatus": "affected"}], "timeline": [{"lang": "en", "time": "2025-06-30T06:18:22.478000+00:00", "value": "Reported to Red Hat."}, {"lang": "en", "time": "2025-06-30T00:00:00+00:00", "value": "Made public."}], "datePublic": "2025-06-30T00:00:00.000Z", "references": [{"url": "https://access.redhat.com/security/cve/CVE-2025-6920", "tags": ["vdb-entry", "x_refsource_REDHAT"]}, {"url": "https://bugzilla.redhat.com/show_bug.cgi?id=2375522", "name": "RHBZ#2375522", "tags": ["issue-tracking", "x_refsource_REDHAT"]}], "workarounds": [{"lang": "en", "value": "Mitigation for this issue is either not available or the currently available options don't meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base or stability."}], "descriptions": [{"lang": "en", "value": "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."}], "problemTypes": [{"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-306", "description": "Missing Authentication for Critical Function"}]}], "providerMetadata": {"orgId": "53f830b8-0a3f-465b-8143-3b8a9948e749", "shortName": "redhat", "dateUpdated": "2025-11-20T20:59:11.209Z"}, "x_redhatCweChain": "CWE-306: Missing Authentication for Critical Function"}}, "cveMetadata": {"cveId": "CVE-2025-6920", "state": "PUBLISHED", "dateUpdated": "2025-11-20T20:59:11.209Z", "dateReserved": "2025-06-30T09:05:19.410Z", "assignerOrgId": "53f830b8-0a3f-465b-8143-3b8a9948e749", "datePublished": "2025-07-01T13:16:17.180Z", "assignerShortName": "redhat"}, "dataVersion": "5.2"}

{"affected": [{"affectedData": [{"collectionURL": "https://access.redhat.com/downloads/content/package-browser/", "cpes": ["cpe:/a:redhat:ai_inference_server:3"], "defaultStatus": "affected", "packageName": "rhaiis/vllm-cuda-rhel9", "product": "Red Hat AI Inference Server", "vendor": "Red Hat"}, {"collectionURL": "https://access.redhat.com/downloads/content/package-browser/", "cpes": ["cpe:/a:redhat:ai_inference_server:3"], "defaultStatus": "affected", "packageName": "rhaiis/vllm-rocm-rhel9", "product": "Red Hat AI Inference Server", "vendor": "Red Hat"}], "source": "secalert@redhat.com"}], "configurations": [{"nodes": [{"cpeMatch": [{"criteria": "cpe:2.3:a:redhat:ai_inference_server:-:*:*:*:*:*:*:*", "matchCriteriaId": "C7E705EE-0973-438E-A35F-3A774ACADF67", "vulnerable": true}], "negate": false, "operator": "OR"}]}], "cveTags": [], "descriptions": [{"lang": "en", "value": "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."}, {"lang": "es", "value": "Se detect\u00f3 una falla en el mecanismo de aplicaci\u00f3n de la autenticaci\u00f3n de una API de inferencia de modelos en ai-inference-server. Se espera que todos los endpoints /v1/* apliquen la validaci\u00f3n de la clave API. Sin embargo, el endpoint POST /invocations no lo hizo, lo que result\u00f3 en una omisi\u00f3n de la autenticaci\u00f3n. Esta vulnerabilidad permite a usuarios no autorizados acceder a las mismas funciones de inferencia disponibles en endpoints protegidos, lo que podr\u00eda exponer funcionalidades sensibles o permitir el acceso no deseado a recursos del backend."}], "id": "CVE-2025-6920", "lastModified": "2026-06-17T10:02:52.403", "metrics": {"cvssMetricV31": [{"cvssData": {"attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "NONE", "baseScore": 5.3, "baseSeverity": "MEDIUM", "confidentialityImpact": "LOW", "integrityImpact": "NONE", "privilegesRequired": "NONE", "scope": "UNCHANGED", "userInteraction": "NONE", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N", "version": "3.1"}, "exploitabilityScore": 3.9, "impactScore": 1.4, "source": "secalert@redhat.com", "type": "Secondary"}], "ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2025-6920", "options": [{"exploitation": "none"}, {"automatable": "yes"}, {"technicalImpact": "partial"}], "role": "CISA Coordinator", "timestamp": "2025-07-01T13:30:12.685492Z", "version": "2.0.3"}}]}, "published": "2025-07-01T14:15:41.690", "references": [{"source": "secalert@redhat.com", "tags": ["Vendor Advisory"], "url": "https://access.redhat.com/security/cve/CVE-2025-6920"}, {"source": "secalert@redhat.com", "tags": ["Issue Tracking", "Vendor Advisory"], "url": "https://bugzilla.redhat.com/show_bug.cgi?id=2375522"}], "sourceIdentifier": "secalert@redhat.com", "vulnStatus": "Analyzed", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-306"}], "source": "secalert@redhat.com", "type": "Secondary"}]}

{"bugzilla": {"description": "ai-inference-server: Authentication Bypass via Unprotected Inference Endpoint in API", "id": "2375522", "url": "https://bugzilla.redhat.com/show_bug.cgi?id=2375522"}, "csaw": false, "cvss3": {"cvss3_base_score": "5.3", "cvss3_scoring_vector": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N", "status": "draft"}, "cwe": "CWE-306", "details": ["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.", "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."], "mitigation": {"lang": "en:us", "value": "Mitigation for this issue is either not available or the currently available options don't meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base or stability."}, "name": "CVE-2025-6920", "package_state": [{"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaiis/vllm-cuda-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaiis/vllm-rocm-rhel9", "product_name": "Red Hat AI Inference Server"}], "public_date": "2025-06-30T00:00:00Z", "references": ["https://www.cve.org/CVERecord?id=CVE-2025-6920\nhttps://nvd.nist.gov/vuln/detail/CVE-2025-6920"], "statement": "Red Hat Product Security has rated the severity of this issue as Moderate, based on the fact that it enables remote, unauthenticated access to protected inference features. While this does not directly compromise system integrity or availability, it bypasses intended access controls and exposes functionality to potential abuse. The core issue stems from insufficient enforcement of authentication on the /invocations endpoint.", "threat_severity": "Moderate"}

{}