CVE-2026-115911

{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-115911", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "state": "PUBLISHED", "assignerShortName": "GitHub_M", "dateReserved": "2026-10-23T20:21:45.107Z", "datePublished": "2026-10-26T16:47:59.377Z", "dateUpdated": "2026-10-30T14:20:51.484Z"}, "containers": {"cna": {"title": "vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool", "problemTypes": [{"descriptions": [{"cweId": "CWE-400", "lang": "en", "description": "CWE-400: Uncontrolled Resource Consumption", "type": "CWE"}]}, {"descriptions": [{"cweId": "CWE-770", "lang": "en", "description": "CWE-770: Allocation of Resources Without Limits or Throttling", "type": "CWE"}]}, {"descriptions": [{"cweId": "CWE-834", "lang": "en", "description": "CWE-834: Excessive Iteration", "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-542m-9234-8gvf", "tags": ["x_refsource_CONFIRM"], "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-542m-9234-8gvf"}, {"name": "https://github.com/vllm-project/vllm/pull/50300", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/pull/50300"}, {"name": "https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134"}, {"name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"}], "affected": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"version": ">= 0.19.0, < 0.32.0", "status": "affected"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2026-10-26T16:47:59.377Z"}, "descriptions": [{"lang": "en", "value": "vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by tokenizer.apply_chat_template() without a wall-clock timeout, output-size limit, or iteration bound. Rendering runs in a ThreadPoolExecutor with one worker by default, so a nonterminating render can block /v1/responses and other chat-template users after the request ends, while an output-expanding render can exhaust server memory. Harmony models are not affected because they do not use this Jinja path. This issue is fixed in version 0.32.0."}], "source": {"advisory": "GHSA-542m-9234-8gvf", "discovery": "UNKNOWN"}}, "adp": [{"metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2026-10-30T14:20:35.704686Z", "id": "CVE-2026-115911", "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": "2026-10-30T14:20:51.484Z"}}]}}

{"dataType": "CVE_RECORD", "containers": {"adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2026-115911", "role": "CISA Coordinator", "options": [{"Exploitation": "none"}, {"Automatable": "no"}, {"Technical Impact": "partial"}], "version": "2.0.3", "timestamp": "2026-10-30T14:20:35.704686Z"}}}], "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-10-30T14:20:46.051Z"}}], "cna": {"title": "vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool", "source": {"advisory": "GHSA-542m-9234-8gvf", "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": ">= 0.19.0, < 0.32.0"}]}], "references": [{"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-542m-9234-8gvf", "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-542m-9234-8gvf", "tags": ["x_refsource_CONFIRM"]}, {"url": "https://github.com/vllm-project/vllm/pull/50300", "name": "https://github.com/vllm-project/vllm/pull/50300", "tags": ["x_refsource_MISC"]}, {"url": "https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134", "name": "https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134", "tags": ["x_refsource_MISC"]}, {"url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0", "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0", "tags": ["x_refsource_MISC"]}], "descriptions": [{"lang": "en", "value": "vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by tokenizer.apply_chat_template() without a wall-clock timeout, output-size limit, or iteration bound. Rendering runs in a ThreadPoolExecutor with one worker by default, so a nonterminating render can block /v1/responses and other chat-template users after the request ends, while an output-expanding render can exhaust server memory. Harmony models are not affected because they do not use this Jinja path. This issue is fixed in version 0.32.0."}], "problemTypes": [{"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-400", "description": "CWE-400: Uncontrolled Resource Consumption"}]}, {"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-770", "description": "CWE-770: Allocation of Resources Without Limits or Throttling"}]}, {"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-834", "description": "CWE-834: Excessive Iteration"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2026-10-26T16:47:59.377Z"}}}, "cveMetadata": {"cveId": "CVE-2026-115911", "state": "PUBLISHED", "dateUpdated": "2026-10-30T14:20:51.484Z", "dateReserved": "2026-10-23T20:21:45.107Z", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "datePublished": "2026-10-26T16:47:59.377Z", "assignerShortName": "GitHub_M"}, "dataVersion": "5.2"}

{"affected": [{"affectedData": [{"product": "vllm", "vendor": "vllm-project", "versions": [{"status": "affected", "version": ">= 0.19.0, < 0.32.0"}]}], "source": "security-advisories@github.com"}], "configurations": [{"nodes": [{"cpeMatch": [{"criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*", "matchCriteriaId": "29923C7C-A5D6-4405-85C7-5678B17164B4", "versionEndExcluding": "0.32.0", "versionStartIncluding": "0.19.0", "vulnerable": true}], "negate": false, "operator": "OR"}]}], "cveTags": [], "descriptions": [{"lang": "en", "value": "vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by tokenizer.apply_chat_template() without a wall-clock timeout, output-size limit, or iteration bound. Rendering runs in a ThreadPoolExecutor with one worker by default, so a nonterminating render can block /v1/responses and other chat-template users after the request ends, while an output-expanding render can exhaust server memory. Harmony models are not affected because they do not use this Jinja path. This issue is fixed in version 0.32.0."}], "id": "CVE-2026-115911", "lastModified": "2026-10-30T15:16:45.860", "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-2026-115911", "options": [{"exploitation": "none"}, {"automatable": "no"}, {"technicalImpact": "partial"}], "role": "CISA Coordinator", "timestamp": "2026-10-30T14:20:35.704686Z", "version": "2.0.3"}}]}, "published": "2026-10-26T17:17:18.753", "references": [{"source": "security-advisories@github.com", "tags": ["Patch"], "url": "https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134"}, {"source": "security-advisories@github.com", "tags": ["Patch"], "url": "https://github.com/vllm-project/vllm/pull/50300"}, {"source": "security-advisories@github.com", "tags": ["Release Notes"], "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"}, {"source": "security-advisories@github.com", "tags": ["Patch", "Vendor Advisory"], "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-542m-9234-8gvf"}], "sourceIdentifier": "security-advisories@github.com", "vulnStatus": "Analyzed", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-400"}, {"lang": "en", "value": "CWE-770"}, {"lang": "en", "value": "CWE-834"}], "source": "security-advisories@github.com", "type": "Secondary"}]}

{"bugzilla": {"description": "vllm: vLLM: Denial of Service via unbounded chat template rendering", "id": "2560960", "url": "https://bugzilla.redhat.com/show_bug.cgi?id=2560960"}, "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": ["A flaw was found in vLLM. An authenticated remote attacker or a malicious model repository can cause a Denial of Service (DoS) by providing a specially crafted chat template. Because templates are rendered without execution timeouts or resource limits, processing the input can permanently block worker threads or exhaust system memory, rendering the service unresponsive or causing it to crash."], "name": "CVE-2026-115911", "package_state": [{"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii-fast/vllm-cpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii-fast/vllm-cuda-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii-fast/vllm-gaudi-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii-fast/vllm-neuron-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii-fast/vllm-omni-cuda-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii-fast/vllm-rocm-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii-fast/vllm-spyre-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii-fast/vllm-tpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii/vllm-cpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii/vllm-cuda-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii/vllm-gaudi-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii/vllm-neuron-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii/vllm-rocm-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii/vllm-spyre-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii/vllm-tpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Fix deferred", "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": "Fix deferred", "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": "Fix deferred", "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": "Fix deferred", "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": "Fix deferred", "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": "Fix deferred", "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": "Fix deferred", "package_name": "rhelai3/bootc-rocm-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Fix deferred", "package_name": "rhoai/odh-kserve-agent-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Fix deferred", "package_name": "rhoai/odh-kserve-controller-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Fix deferred", "package_name": "rhoai/odh-kserve-router-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Fix deferred", "package_name": "rhoai/odh-kserve-storage-initializer-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Fix deferred", "package_name": "rhoai/odh-llm-d-kv-cache-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Fix deferred", "package_name": "rhoai/odh-th-torch-cuda-py312-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Fix deferred", "package_name": "rhoai/odh-vllm-cuda-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Fix deferred", "package_name": "rhoai/odh-vllm-gaudi-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Fix deferred", "package_name": "rhoai/odh-vllm-rocm-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}], "public_date": "2026-10-26T16:47:59Z", "references": ["https://www.cve.org/CVERecord?id=CVE-2026-115911\nhttps://nvd.nist.gov/vuln/detail/CVE-2026-115911\nhttps://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134\nhttps://github.com/vllm-project/vllm/pull/50300\nhttps://github.com/vllm-project/vllm/releases/tag/v0.32.0\nhttps://github.com/vllm-project/vllm/security/advisories/GHSA-542m-9234-8gvf"], "threat_severity": "Moderate"}

{"affected": [{"configurations": [{"platform": null, "status": "affected", "versions": {"scheme": "semver", "value": "[0.19.0,0.32.0)"}}], "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"}, {"configurations": [{"platform": null, "status": "affected", "versions": {"scheme": "semver", "value": "[0.19.0,0.32.0)"}}], "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": "2026-10-26T18:30:14.333859+00:00", "updated": "2026-10-26T18:30:14.675252+00:00", "vendors": ["vllm", "vllm$PRODUCT$vllm", "vllm-project", "vllm-project$PRODUCT$vllm"]}