CVE-2025-32381

{"dataType": "CVE_RECORD", "dataVersion": "5.1", "cveMetadata": {"cveId": "CVE-2025-32381", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "state": "PUBLISHED", "assignerShortName": "GitHub_M", "dateReserved": "2025-04-06T19:46:02.462Z", "datePublished": "2025-04-09T16:00:10.642Z", "dateUpdated": "2025-04-09T20:43:33.169Z"}, "containers": {"cna": {"title": "Denial of Service by abusing xgrammar unbounded cache in memory", "problemTypes": [{"descriptions": [{"cweId": "CWE-770", "lang": "en", "description": "CWE-770: Allocation of Resources Without Limits or Throttling", "type": "CWE"}]}], "metrics": [{"cvssV3_1": {"attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "HIGH", "baseScore": 6.5, "baseSeverity": "MEDIUM", "confidentialityImpact": "NONE", "integrityImpact": "NONE", "privilegesRequired": "LOW", "scope": "UNCHANGED", "userInteraction": "NONE", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H", "version": "3.1"}}], "references": [{"name": "https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3", "tags": ["x_refsource_CONFIRM"], "url": "https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3"}, {"name": "https://github.com/mlc-ai/xgrammar/pull/243", "tags": ["x_refsource_MISC"], "url": "https://github.com/mlc-ai/xgrammar/pull/243"}, {"name": "https://github.com/vllm-project/vllm/pull/16283", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/pull/16283"}], "affected": [{"vendor": "mlc-ai", "product": "xgrammar", "versions": [{"version": "< 0.1.18", "status": "affected"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2025-04-09T16:00:10.642Z"}, "descriptions": [{"lang": "en", "value": "XGrammar is an open-source library for efficient, flexible, and portable structured generation. Prior to 0.1.18, Xgrammar includes a cache for compiled grammars to increase performance with repeated use of the same grammar. This cache is held in memory. Since the cache is unbounded, a system making use of xgrammar can be abused to fill up a host's memory and case a denial of service. For example, sending many small requests to an LLM inference server with unique JSON schemas would eventually cause this denial of service to occur. This vulnerability is fixed in 0.1.18."}], "source": {"advisory": "GHSA-389x-67px-mjg3", "discovery": "UNKNOWN"}}, "adp": [{"metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2025-04-09T17:26:48.431586Z", "id": "CVE-2025-32381", "options": [{"Exploitation": "none"}, {"Automatable": "no"}, {"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": "2025-04-09T20:43:33.169Z"}}]}}

{"dataType": "CVE_RECORD", "dataVersion": "5.1", "cveMetadata": {"cveId": "CVE-2025-32381", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "state": "PUBLISHED", "assignerShortName": "GitHub_M", "dateReserved": "2025-04-06T19:46:02.462Z", "datePublished": "2025-04-09T16:00:10.642Z", "dateUpdated": "2025-04-09T20:43:33.169Z"}, "containers": {"cna": {"title": "Denial of Service by abusing xgrammar unbounded cache in memory", "problemTypes": [{"descriptions": [{"cweId": "CWE-770", "lang": "en", "description": "CWE-770: Allocation of Resources Without Limits or Throttling", "type": "CWE"}]}], "metrics": [{"cvssV3_1": {"attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "HIGH", "baseScore": 6.5, "baseSeverity": "MEDIUM", "confidentialityImpact": "NONE", "integrityImpact": "NONE", "privilegesRequired": "LOW", "scope": "UNCHANGED", "userInteraction": "NONE", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H", "version": "3.1"}}], "references": [{"name": "https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3", "tags": ["x_refsource_CONFIRM"], "url": "https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3"}, {"name": "https://github.com/mlc-ai/xgrammar/pull/243", "tags": ["x_refsource_MISC"], "url": "https://github.com/mlc-ai/xgrammar/pull/243"}, {"name": "https://github.com/vllm-project/vllm/pull/16283", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/pull/16283"}], "affected": [{"vendor": "mlc-ai", "product": "xgrammar", "versions": [{"version": "< 0.1.18", "status": "affected"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2025-04-09T16:00:10.642Z"}, "descriptions": [{"lang": "en", "value": "XGrammar is an open-source library for efficient, flexible, and portable structured generation. Prior to 0.1.18, Xgrammar includes a cache for compiled grammars to increase performance with repeated use of the same grammar. This cache is held in memory. Since the cache is unbounded, a system making use of xgrammar can be abused to fill up a host's memory and case a denial of service. For example, sending many small requests to an LLM inference server with unique JSON schemas would eventually cause this denial of service to occur. This vulnerability is fixed in 0.1.18."}], "source": {"advisory": "GHSA-389x-67px-mjg3", "discovery": "UNKNOWN"}}, "adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2025-32381", "role": "CISA Coordinator", "options": [{"Exploitation": "none"}, {"Automatable": "no"}, {"Technical Impact": "partial"}], "version": "2.0.3", "timestamp": "2025-04-09T17:26:48.431586Z"}}}], "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2025-04-09T17:27:09.287Z"}}]}}

{"affected": [{"affectedData": [{"product": "xgrammar", "vendor": "mlc-ai", "versions": [{"status": "affected", "version": "< 0.1.18"}]}], "source": "security-advisories@github.com"}], "configurations": [{"nodes": [{"cpeMatch": [{"criteria": "cpe:2.3:a:mlc-ai:xgrammar:*:*:*:*:*:*:*:*", "matchCriteriaId": "C4908F3A-2B0B-4DEF-B728-520E0DCA5338", "versionEndExcluding": "0.1.18", "vulnerable": true}], "negate": false, "operator": "OR"}]}], "cveTags": [], "descriptions": [{"lang": "en", "value": "XGrammar is an open-source library for efficient, flexible, and portable structured generation. Prior to 0.1.18, Xgrammar includes a cache for compiled grammars to increase performance with repeated use of the same grammar. This cache is held in memory. Since the cache is unbounded, a system making use of xgrammar can be abused to fill up a host's memory and case a denial of service. For example, sending many small requests to an LLM inference server with unique JSON schemas would eventually cause this denial of service to occur. This vulnerability is fixed in 0.1.18."}, {"lang": "es", "value": "XGrammar es una librer\u00eda de c\u00f3digo abierto para la generaci\u00f3n estructurada eficiente, flexible y port\u00e1til. Antes de la versi\u00f3n 0.1.18, Xgrammar inclu\u00eda una cach\u00e9 para gram\u00e1ticas compiladas que mejoraba el rendimiento con el uso repetido de la misma gram\u00e1tica. Esta cach\u00e9 se almacena en memoria. Dado que la cach\u00e9 es ilimitada, un sistema que utiliza xgrammar puede ser utilizado de forma abusiva para saturar la memoria del host y provocar una denegaci\u00f3n de servicio. Por ejemplo, enviar muchas solicitudes peque\u00f1as a un servidor de inferencia LLM con esquemas JSON \u00fanicos podr\u00eda provocar esta denegaci\u00f3n de servicio. Esta vulnerabilidad se corrigi\u00f3 en la versi\u00f3n 0.1.18."}], "id": "CVE-2025-32381", "lastModified": "2026-06-17T09:11:54.667", "metrics": {"cvssMetricV31": [{"cvssData": {"attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "HIGH", "baseScore": 6.5, "baseSeverity": "MEDIUM", "confidentialityImpact": "NONE", "integrityImpact": "NONE", "privilegesRequired": "LOW", "scope": "UNCHANGED", "userInteraction": "NONE", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H", "version": "3.1"}, "exploitabilityScore": 2.8, "impactScore": 3.6, "source": "security-advisories@github.com", "type": "Secondary"}], "ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2025-32381", "options": [{"exploitation": "none"}, {"automatable": "no"}, {"technicalImpact": "partial"}], "role": "CISA Coordinator", "timestamp": "2025-04-09T17:26:48.431586Z", "version": "2.0.3"}}]}, "published": "2025-04-09T16:15:26.210", "references": [{"source": "security-advisories@github.com", "tags": ["Issue Tracking", "Patch"], "url": "https://github.com/mlc-ai/xgrammar/pull/243"}, {"source": "security-advisories@github.com", "tags": ["Vendor Advisory"], "url": "https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3"}, {"source": "security-advisories@github.com", "tags": ["Issue Tracking", "Patch"], "url": "https://github.com/vllm-project/vllm/pull/16283"}], "sourceIdentifier": "security-advisories@github.com", "vulnStatus": "Analyzed", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-770"}], "source": "security-advisories@github.com", "type": "Secondary"}]}

{"bugzilla": {"description": "xgrammar: xgrammar Vulnerable to Denial of Service (DoS) by abusing unbounded cache in memory", "id": "2358639", "url": "https://bugzilla.redhat.com/show_bug.cgi?id=2358639"}, "csaw": false, "cvss3": {"cvss3_base_score": "6.5", "cvss3_scoring_vector": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H", "status": "draft"}, "cwe": "CWE-770", "details": ["XGrammar is an open-source library for efficient, flexible, and portable structured generation. Prior to 0.1.18, Xgrammar includes a cache for compiled grammars to increase performance with repeated use of the same grammar. This cache is held in memory. Since the cache is unbounded, a system making use of xgrammar can be abused to fill up a host's memory and case a denial of service. For example, sending many small requests to an LLM inference server with unique JSON schemas would eventually cause this denial of service to occur. This vulnerability is fixed in 0.1.18.", "A flaw was found in Xgrammar. This vulnerability allows a denial of service (DoS) via unbounded memory usage when handling a large number of unique grammar inputs from untrusted sources."], "mitigation": {"lang": "en:us", "value": "Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base or stability."}, "name": "CVE-2025-32381", "package_state": [{"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/ui-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}], "public_date": "2025-04-09T13:08:59Z", "references": ["https://www.cve.org/CVERecord?id=CVE-2025-32381\nhttps://nvd.nist.gov/vuln/detail/CVE-2025-32381\nhttps://github.com/mlc-ai/xgrammar\nhttps://github.com/mlc-ai/xgrammar/pull/243\nhttps://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3"], "threat_severity": "Moderate"}

{}