CVE-2026-54234

{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-54234", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "state": "PUBLISHED", "assignerShortName": "GitHub_M", "dateReserved": "2026-06-12T16:25:43.084Z", "datePublished": "2026-07-06T19:49:20.481Z", "dateUpdated": "2026-07-07T14:13:34.348Z"}, "containers": {"cna": {"title": "vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection", "problemTypes": [{"descriptions": [{"cweId": "CWE-20", "lang": "en", "description": "CWE-20: Improper Input Validation", "type": "CWE"}]}, {"descriptions": [{"cweId": "CWE-1284", "lang": "en", "description": "CWE-1284: Improper Validation of Specified Quantity in Input", "type": "CWE"}]}], "metrics": [{"cvssV3_1": {"attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "HIGH", "baseScore": 7.5, "baseSeverity": "HIGH", "confidentialityImpact": "NONE", "integrityImpact": "NONE", "privilegesRequired": "NONE", "scope": "UNCHANGED", "userInteraction": "NONE", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H", "version": "3.1"}}], "references": [{"name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4f", "tags": ["x_refsource_CONFIRM"], "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4f"}, {"name": "https://github.com/vllm-project/vllm/pull/44744", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/pull/44744"}, {"name": "https://github.com/vllm-project/vllm/commit/8a5cf1ccd65e8ac7635c402c1ec0b08988bc26ca", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/commit/8a5cf1ccd65e8ac7635c402c1ec0b08988bc26ca"}], "affected": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"version": "< 0.24.0", "status": "affected"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2026-07-06T19:49:20.481Z"}, "descriptions": [{"lang": "en", "value": "vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a frontend-legal multi-request speculative decoding workload can cause the rejection sampler to produce a recovered token equal to the model vocabulary size boundary value, which is then converted to negative one when the engine selects the next live token for a request and is written back into the drafter's input ids; that out-of-vocabulary value is later consumed by the model's embedding and attention path and crashes the engine worker with a GPU device-side assertion. The same triggering request sequence is reachable through the public gRPC Generate and Abort endpoints, so a remote client that can send generation requests can crash the shared engine worker, aborting concurrent requests and causing a service-wide denial of service for other clients of the deployment until the worker is restarted. This issue is fixed in version 0.24.0."}], "source": {"advisory": "GHSA-8wr5-jm2h-8r4f", "discovery": "UNKNOWN"}}, "adp": [{"references": [{"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4f", "tags": ["exploit"]}], "metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2026-07-07T14:12:43.565166Z", "id": "CVE-2026-54234", "options": [{"Exploitation": "poc"}, {"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": "2026-07-07T14:13:34.348Z"}}]}}

{"dataType": "CVE_RECORD", "containers": {"adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2026-54234", "role": "CISA Coordinator", "options": [{"Exploitation": "poc"}, {"Automatable": "yes"}, {"Technical Impact": "partial"}], "version": "2.0.3", "timestamp": "2026-07-07T14:12:43.565166Z"}}}], "references": [{"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4f", "tags": ["exploit"]}], "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-07-07T14:13:30.358Z"}}], "cna": {"title": "vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection", "source": {"advisory": "GHSA-8wr5-jm2h-8r4f", "discovery": "UNKNOWN"}, "metrics": [{"cvssV3_1": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 7.5, "attackVector": "NETWORK", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H", "integrityImpact": "NONE", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "NONE"}}], "affected": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"status": "affected", "version": "< 0.24.0"}]}], "references": [{"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4f", "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4f", "tags": ["x_refsource_CONFIRM"]}, {"url": "https://github.com/vllm-project/vllm/pull/44744", "name": "https://github.com/vllm-project/vllm/pull/44744", "tags": ["x_refsource_MISC"]}, {"url": "https://github.com/vllm-project/vllm/commit/8a5cf1ccd65e8ac7635c402c1ec0b08988bc26ca", "name": "https://github.com/vllm-project/vllm/commit/8a5cf1ccd65e8ac7635c402c1ec0b08988bc26ca", "tags": ["x_refsource_MISC"]}], "descriptions": [{"lang": "en", "value": "vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a frontend-legal multi-request speculative decoding workload can cause the rejection sampler to produce a recovered token equal to the model vocabulary size boundary value, which is then converted to negative one when the engine selects the next live token for a request and is written back into the drafter's input ids; that out-of-vocabulary value is later consumed by the model's embedding and attention path and crashes the engine worker with a GPU device-side assertion. The same triggering request sequence is reachable through the public gRPC Generate and Abort endpoints, so a remote client that can send generation requests can crash the shared engine worker, aborting concurrent requests and causing a service-wide denial of service for other clients of the deployment until the worker is restarted. This issue is fixed in version 0.24.0."}], "problemTypes": [{"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-20", "description": "CWE-20: Improper Input Validation"}]}, {"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-1284", "description": "CWE-1284: Improper Validation of Specified Quantity in Input"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2026-07-06T19:49:20.481Z"}}}, "cveMetadata": {"cveId": "CVE-2026-54234", "state": "PUBLISHED", "dateUpdated": "2026-07-07T14:13:34.348Z", "dateReserved": "2026-06-12T16:25:43.084Z", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "datePublished": "2026-07-06T19:49:20.481Z", "assignerShortName": "GitHub_M"}, "dataVersion": "5.2"}

{"affected": [{"affectedData": [{"product": "vllm", "vendor": "vllm-project", "versions": [{"status": "affected", "version": "< 0.24.0"}]}], "source": "security-advisories@github.com"}], "configurations": [{"nodes": [{"cpeMatch": [{"criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*", "matchCriteriaId": "0AF36274-AF6A-4915-8D2E-3603CF15D863", "versionEndExcluding": "0.24.0", "vulnerable": true}], "negate": false, "operator": "OR"}]}], "cveTags": [], "descriptions": [{"lang": "en", "value": "vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a frontend-legal multi-request speculative decoding workload can cause the rejection sampler to produce a recovered token equal to the model vocabulary size boundary value, which is then converted to negative one when the engine selects the next live token for a request and is written back into the drafter's input ids; that out-of-vocabulary value is later consumed by the model's embedding and attention path and crashes the engine worker with a GPU device-side assertion. The same triggering request sequence is reachable through the public gRPC Generate and Abort endpoints, so a remote client that can send generation requests can crash the shared engine worker, aborting concurrent requests and causing a service-wide denial of service for other clients of the deployment until the worker is restarted. This issue is fixed in version 0.24.0."}, {"lang": "es", "value": "vLLM es un motor de inferencia y servicio de alto rendimiento y eficiente en memoria para LLMs. Antes de la versi\u00f3n 0.24.0, una carga de trabajo de decodificaci\u00f3n especulativa de m\u00faltiples solicitudes v\u00e1lida para el frontend puede hacer que el muestreador de rechazo produzca un token recuperado igual al valor l\u00edmite del tama\u00f1o del vocabulario del modelo, que luego se convierte en menos uno cuando el motor selecciona el siguiente token vivo para una solicitud y se vuelve a escribir en los IDs de entrada del drafter; ese valor fuera de vocabulario es consumido posteriormente por la ruta de incrustaci\u00f3n y atenci\u00f3n del modelo y bloquea el worker del motor con una aserci\u00f3n del lado del dispositivo GPU. La misma secuencia de solicitud desencadenante es accesible a trav\u00e9s de los puntos finales p\u00fablicos gRPC Generate y Abort, por lo que un cliente remoto que puede enviar solicitudes de generaci\u00f3n puede bloquear el worker del motor compartido, abortando solicitudes concurrentes y causando una denegaci\u00f3n de servicio a nivel de servicio para otros clientes de la implementaci\u00f3n hasta que se reinicie el worker. Este problema est\u00e1 solucionado en la versi\u00f3n 0.24.0."}], "id": "CVE-2026-54234", "lastModified": "2026-10-25T20:10:00.147", "metrics": {"cvssMetricV31": [{"cvssData": {"attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "HIGH", "baseScore": 7.5, "baseSeverity": "HIGH", "confidentialityImpact": "NONE", "integrityImpact": "NONE", "privilegesRequired": "NONE", "scope": "UNCHANGED", "userInteraction": "NONE", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H", "version": "3.1"}, "exploitabilityScore": 3.9, "impactScore": 3.6, "source": "security-advisories@github.com", "type": "Secondary"}], "ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-54234", "options": [{"exploitation": "poc"}, {"automatable": "yes"}, {"technicalImpact": "partial"}], "role": "CISA Coordinator", "timestamp": "2026-07-07T14:12:43.565166Z", "version": "2.0.3"}}]}, "published": "2026-07-06T21:16:56.477", "references": [{"source": "security-advisories@github.com", "tags": ["Patch"], "url": "https://github.com/vllm-project/vllm/commit/8a5cf1ccd65e8ac7635c402c1ec0b08988bc26ca"}, {"source": "security-advisories@github.com", "tags": ["Issue Tracking", "Patch"], "url": "https://github.com/vllm-project/vllm/pull/44744"}, {"source": "security-advisories@github.com", "tags": ["Vendor Advisory", "Exploit"], "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4f"}, {"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "tags": ["Vendor Advisory", "Exploit"], "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4f"}], "sourceIdentifier": "security-advisories@github.com", "vulnStatus": "Analyzed", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-20"}, {"lang": "en", "value": "CWE-1284"}], "source": "security-advisories@github.com", "type": "Secondary"}]}

{"bugzilla": {"description": "vllm: vLLM: Denial of Service via malformed speculative decoding workload", "id": "2497515", "url": "https://bugzilla.redhat.com/show_bug.cgi?id=2497515"}, "csaw": false, "cvss3": {"cvss3_base_score": "7.5", "cvss3_scoring_vector": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H", "status": "draft"}, "cwe": "CWE-125", "details": ["vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a frontend-legal multi-request speculative decoding workload can cause the rejection sampler to produce a recovered token equal to the model vocabulary size boundary value, which is then converted to negative one when the engine selects the next live token for a request and is written back into the drafter's input ids; that out-of-vocabulary value is later consumed by the model's embedding and attention path and crashes the engine worker with a GPU device-side assertion. The same triggering request sequence is reachable through the public gRPC Generate and Abort endpoints, so a remote client that can send generation requests can crash the shared engine worker, aborting concurrent requests and causing a service-wide denial of service for other clients of the deployment until the worker is restarted. This issue is fixed in version 0.24.0.", "A flaw was found in vLLM, a high-throughput and memory-efficient inference and serving engine for Large Language Models (LLMs). A remote attacker can exploit this vulnerability by sending a specially crafted multi-request speculative decoding workload through public gRPC Generate and Abort endpoints. This malformed workload can cause the rejection sampler to produce an out-of-vocabulary token, which then crashes the engine worker. This leads to a service-wide Denial of Service (DoS) for all clients until the worker is restarted."], "mitigation": {"lang": "en:us", "value": "To mitigate this issue, restrict network access to the vLLM inference engine's gRPC Generate and Abort endpoints. Configure firewall rules to limit incoming connections to trusted clients or internal networks only. This will prevent remote, unauthenticated attackers from sending malformed workloads and triggering a denial of service. If the service is exposed via a proxy or load balancer, ensure that access controls are in place at that layer."}, "name": "CVE-2026-54234", "package_state": [{"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaiis/vllm-cpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"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-neuron-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"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaiis/vllm-spyre-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaiis/vllm-tpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaii/vllm-cpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaii/vllm-cuda-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaii/vllm-gaudi-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaii/vllm-neuron-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaii/vllm-rocm-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaii/vllm-spyre-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaii/vllm-tpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Affected", "package_name": "rhelai3/bootc-aws-cuda-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Affected", "package_name": "rhelai3/bootc-azure-cuda-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Affected", "package_name": "rhelai3/bootc-azure-rocm-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Affected", "package_name": "rhelai3/bootc-cuda-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Affected", "package_name": "rhelai3/bootc-gaudi-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Affected", "package_name": "rhelai3/bootc-gcp-cuda-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Affected", "package_name": "rhelai3/bootc-rocm-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Not affected", "package_name": "rhoai/odh-kserve-agent-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Not affected", "package_name": "rhoai/odh-kserve-controller-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Not affected", "package_name": "rhoai/odh-kserve-router-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Not affected", "package_name": "rhoai/odh-kserve-storage-initializer-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Affected", "package_name": "rhoai/odh-llm-d-kv-cache-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Affected", "package_name": "rhoai/odh-vllm-gaudi-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}], "public_date": "2026-07-06T19:49:20Z", "references": ["https://www.cve.org/CVERecord?id=CVE-2026-54234\nhttps://nvd.nist.gov/vuln/detail/CVE-2026-54234\nhttps://github.com/vllm-project/vllm/commit/8a5cf1ccd65e8ac7635c402c1ec0b08988bc26ca\nhttps://github.com/vllm-project/vllm/pull/44744\nhttps://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4f"], "statement": "This Important denial of service flaw in vLLM, utilized by Red Hat AI Inference Server, Red Hat Enterprise Linux AI, and Red Hat OpenShift AI, allows a remote attacker to crash the engine worker. By sending a specially crafted multi-request speculative decoding workload to public gRPC endpoints, an attacker can trigger an out-of-vocabulary token, leading to a service-wide disruption for all connected clients.", "threat_severity": "Important"}

{"affected": [{"configurations": [{"platform": null, "status": "affected", "versions": {"scheme": "semver", "value": "[0,0.24.0)"}}], "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": "2026-07-06T22:00:14.241506+00:00", "updated": "2026-08-01T18:30:04.994390+00:00", "vendors": ["vllm-project", "vllm-project$PRODUCT$vllm"]}