{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-44223", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "state": "PUBLISHED", "assignerShortName": "GitHub_M", "dateReserved": "2026-05-05T15:42:40.518Z", "datePublished": "2026-05-12T19:58:40.862Z", "dateUpdated": "2026-05-15T14:46:25.695Z"}, "containers": {"cna": {"title": "vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters", "problemTypes": [{"descriptions": [{"cweId": "CWE-131", "lang": "en", "description": "CWE-131: Incorrect Calculation of Buffer Size", "type": "CWE"}]}, {"descriptions": [{"cweId": "CWE-704", "lang": "en", "description": "CWE-704: Incorrect Type Conversion or Cast", "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/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw", "tags": ["x_refsource_CONFIRM"], "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw"}, {"name": "https://github.com/vllm-project/vllm/pull/38610", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/pull/38610"}], "affected": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"version": ">= 0.18.0, < 0.20.0", "status": "affected"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2026-05-12T19:58:40.862Z"}, "descriptions": [{"lang": "en", "value": "vLLM is an inference and serving engine for large language models (LLMs). From to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). A single request with a penalty parameter (e.g., \"repetition_penalty\": 1.1) is sufficient to crash the server. This vulnerability is fixed in 0.20.0."}], "source": {"advisory": "GHSA-83vm-p52w-f9pw", "discovery": "UNKNOWN"}}, "adp": [{"references": [{"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw", "tags": ["exploit"]}, {"url": "https://github.com/vllm-project/vllm/pull/38610", "tags": ["exploit"]}], "metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2026-05-15T14:44:05.012494Z", "id": "CVE-2026-44223", "options": [{"Exploitation": "poc"}, {"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": "2026-05-15T14:46:25.695Z"}}]}}

{"dataType": "CVE_RECORD", "containers": {"adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2026-44223", "role": "CISA Coordinator", "options": [{"Exploitation": "poc"}, {"Automatable": "no"}, {"Technical Impact": "partial"}], "version": "2.0.3", "timestamp": "2026-05-15T14:44:05.012494Z"}}}], "references": [{"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw", "tags": ["exploit"]}, {"url": "https://github.com/vllm-project/vllm/pull/38610", "tags": ["exploit"]}], "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-05-15T14:43:40.735Z"}}], "cna": {"title": "vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters", "source": {"advisory": "GHSA-83vm-p52w-f9pw", "discovery": "UNKNOWN"}, "metrics": [{"cvssV3_1": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 6.5, "attackVector": "NETWORK", "baseSeverity": "MEDIUM", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H", "integrityImpact": "NONE", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "LOW", "confidentialityImpact": "NONE"}}], "affected": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"status": "affected", "version": ">= 0.18.0, < 0.20.0"}]}], "references": [{"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw", "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw", "tags": ["x_refsource_CONFIRM"]}, {"url": "https://github.com/vllm-project/vllm/pull/38610", "name": "https://github.com/vllm-project/vllm/pull/38610", "tags": ["x_refsource_MISC"]}], "descriptions": [{"lang": "en", "value": "vLLM is an inference and serving engine for large language models (LLMs). From to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). A single request with a penalty parameter (e.g., \"repetition_penalty\": 1.1) is sufficient to crash the server. This vulnerability is fixed in 0.20.0."}], "problemTypes": [{"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-131", "description": "CWE-131: Incorrect Calculation of Buffer Size"}]}, {"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-704", "description": "CWE-704: Incorrect Type Conversion or Cast"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2026-05-12T19:58:40.862Z"}}}, "cveMetadata": {"cveId": "CVE-2026-44223", "state": "PUBLISHED", "dateUpdated": "2026-05-15T14:46:25.695Z", "dateReserved": "2026-05-05T15:42:40.518Z", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "datePublished": "2026-05-12T19:58:40.862Z", "assignerShortName": "GitHub_M"}, "dataVersion": "5.2"}

{"configurations": [{"nodes": [{"cpeMatch": [{"criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*", "matchCriteriaId": "443F32C2-B323-4FA0-AB97-F6445C91C89E", "versionEndExcluding": "0.20.0", "versionStartIncluding": "0.18.0", "vulnerable": true}], "negate": false, "operator": "OR"}]}], "cveTags": [], "descriptions": [{"lang": "en", "value": "vLLM is an inference and serving engine for large language models (LLMs). From to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). A single request with a penalty parameter (e.g., \"repetition_penalty\": 1.1) is sufficient to crash the server. This vulnerability is fixed in 0.20.0."}], "id": "CVE-2026-44223", "lastModified": "2026-05-15T15:16:52.560", "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"}]}, "published": "2026-05-12T20:16:43.293", "references": [{"source": "security-advisories@github.com", "tags": ["Issue Tracking", "Patch"], "url": "https://github.com/vllm-project/vllm/pull/38610"}, {"source": "security-advisories@github.com", "tags": ["Mitigation", "Vendor Advisory"], "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw"}, {"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "tags": ["Issue Tracking", "Patch"], "url": "https://github.com/vllm-project/vllm/pull/38610"}, {"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "tags": ["Mitigation", "Vendor Advisory"], "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw"}], "sourceIdentifier": "security-advisories@github.com", "vulnStatus": "Modified", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-131"}, {"lang": "en", "value": "CWE-704"}], "source": "security-advisories@github.com", "type": "Secondary"}]}

{}

{"affected": [{"configurations": [{"platform": null, "status": "affected", "versions": {"scheme": "semver", "value": "[0.18.0,0.20.0)"}}], "enrichment": {"confidence": 100.0, "confidence_source": "matching", "scores": [{"score": 100.0, "source": "matching"}]}, "original": {"product": "vllm", "source": "cna", "vendor": "vllm-project"}, "product": "vllm", "vendor": "vllm-project"}], "created": "2026-05-12T21:45:05.382555+00:00", "updated": "2026-05-12T23:15:26.963287+00:00", "vendors": ["vllm-project", "vllm-project$PRODUCT$vllm"]}