{"dataType": "CVE_RECORD", "dataVersion": "5.1", "cveMetadata": {"cveId": "CVE-2025-46570", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "state": "PUBLISHED", "assignerShortName": "GitHub_M", "dateReserved": "2025-04-24T21:10:48.175Z", "datePublished": "2025-05-29T16:32:42.794Z", "dateUpdated": "2025-05-29T18:05:10.768Z"}, "containers": {"cna": {"title": "vLLM\u2019s Chunk-Based Prefix Caching Vulnerable to Potential Timing Side-Channel", "problemTypes": [{"descriptions": [{"cweId": "CWE-208", "lang": "en", "description": "CWE-208: Observable Timing Discrepancy", "type": "CWE"}]}], "metrics": [{"cvssV3_1": {"attackComplexity": "HIGH", "attackVector": "NETWORK", "availabilityImpact": "NONE", "baseScore": 2.6, "baseSeverity": "LOW", "confidentialityImpact": "LOW", "integrityImpact": "NONE", "privilegesRequired": "LOW", "scope": "UNCHANGED", "userInteraction": "REQUIRED", "vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:N/A:N", "version": "3.1"}}], "references": [{"name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-4qjh-9fv9-r85r", "tags": ["x_refsource_CONFIRM"], "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-4qjh-9fv9-r85r"}, {"name": "https://github.com/vllm-project/vllm/pull/17045", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/pull/17045"}, {"name": "https://github.com/vllm-project/vllm/commit/77073c77bc2006eb80ea6d5128f076f5e6c6f54f", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/commit/77073c77bc2006eb80ea6d5128f076f5e6c6f54f"}], "affected": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"version": "< 0.9.0", "status": "affected"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2025-05-29T16:32:42.794Z"}, "descriptions": [{"lang": "en", "value": "vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time to First Token). These timing differences caused by matching chunks are significant enough to be recognized and exploited. This issue has been patched in version 0.9.0."}], "source": {"advisory": "GHSA-4qjh-9fv9-r85r", "discovery": "UNKNOWN"}}, "adp": [{"metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2025-05-29T18:04:57.706360Z", "id": "CVE-2025-46570", "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": "2025-05-29T18:05:10.768Z"}}]}}

{"dataType": "CVE_RECORD", "containers": {"adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2025-46570", "role": "CISA Coordinator", "options": [{"Exploitation": "none"}, {"Automatable": "no"}, {"Technical Impact": "partial"}], "version": "2.0.3", "timestamp": "2025-05-29T18:04:57.706360Z"}}}], "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2025-05-29T18:05:04.545Z"}}], "cna": {"title": "vLLM\u2019s Chunk-Based Prefix Caching Vulnerable to Potential Timing Side-Channel", "source": {"advisory": "GHSA-4qjh-9fv9-r85r", "discovery": "UNKNOWN"}, "metrics": [{"cvssV3_1": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 2.6, "attackVector": "NETWORK", "baseSeverity": "LOW", "vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:N/A:N", "integrityImpact": "NONE", "userInteraction": "REQUIRED", "attackComplexity": "HIGH", "availabilityImpact": "NONE", "privilegesRequired": "LOW", "confidentialityImpact": "LOW"}}], "affected": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"status": "affected", "version": "< 0.9.0"}]}], "references": [{"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-4qjh-9fv9-r85r", "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-4qjh-9fv9-r85r", "tags": ["x_refsource_CONFIRM"]}, {"url": "https://github.com/vllm-project/vllm/pull/17045", "name": "https://github.com/vllm-project/vllm/pull/17045", "tags": ["x_refsource_MISC"]}, {"url": "https://github.com/vllm-project/vllm/commit/77073c77bc2006eb80ea6d5128f076f5e6c6f54f", "name": "https://github.com/vllm-project/vllm/commit/77073c77bc2006eb80ea6d5128f076f5e6c6f54f", "tags": ["x_refsource_MISC"]}], "descriptions": [{"lang": "en", "value": "vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time to First Token). These timing differences caused by matching chunks are significant enough to be recognized and exploited. This issue has been patched in version 0.9.0."}], "problemTypes": [{"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-208", "description": "CWE-208: Observable Timing Discrepancy"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2025-05-29T16:32:42.794Z"}}}, "cveMetadata": {"cveId": "CVE-2025-46570", "state": "PUBLISHED", "dateUpdated": "2025-05-29T18:05:10.768Z", "dateReserved": "2025-04-24T21:10:48.175Z", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "datePublished": "2025-05-29T16:32:42.794Z", "assignerShortName": "GitHub_M"}, "dataVersion": "5.1"}

{"cveTags": [], "descriptions": [{"lang": "en", "value": "vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time to First Token). These timing differences caused by matching chunks are significant enough to be recognized and exploited. This issue has been patched in version 0.9.0."}, {"lang": "es", "value": "vLLM es un motor de inferencia y entrega para modelos de lenguaje grandes (LLM). Antes de la versi\u00f3n 0.9.0, al procesar una nueva solicitud, si el mecanismo PageAttention encuentra un fragmento de prefijo coincidente, el proceso de precompletado se acelera, lo que se refleja en el TTFT (Tiempo hasta el Primer Token). Estas diferencias de tiempo causadas por la coincidencia de fragmentos son lo suficientemente significativas como para ser detectadas y explotadas. Este problema se ha corregido en la versi\u00f3n 0.9.0."}], "id": "CVE-2025-46570", "lastModified": "2025-05-30T16:31:03.107", "metrics": {"cvssMetricV31": [{"cvssData": {"attackComplexity": "HIGH", "attackVector": "NETWORK", "availabilityImpact": "NONE", "baseScore": 2.6, "baseSeverity": "LOW", "confidentialityImpact": "LOW", "integrityImpact": "NONE", "privilegesRequired": "LOW", "scope": "UNCHANGED", "userInteraction": "REQUIRED", "vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:N/A:N", "version": "3.1"}, "exploitabilityScore": 1.2, "impactScore": 1.4, "source": "security-advisories@github.com", "type": "Secondary"}]}, "published": "2025-05-29T17:15:21.327", "references": [{"source": "security-advisories@github.com", "url": "https://github.com/vllm-project/vllm/commit/77073c77bc2006eb80ea6d5128f076f5e6c6f54f"}, {"source": "security-advisories@github.com", "url": "https://github.com/vllm-project/vllm/pull/17045"}, {"source": "security-advisories@github.com", "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-4qjh-9fv9-r85r"}], "sourceIdentifier": "security-advisories@github.com", "vulnStatus": "Awaiting Analysis", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-208"}], "source": "security-advisories@github.com", "type": "Primary"}]}

{"bugzilla": {"description": "vllm: vLLM\u2019s Chunk-Based Prefix Caching Vulnerable to Potential Timing Side-Channel", "id": "2369223", "url": "https://bugzilla.redhat.com/show_bug.cgi?id=2369223"}, "csaw": false, "cvss3": {"cvss3_base_score": "2.6", "cvss3_scoring_vector": "CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:N/A:N", "status": "draft"}, "cwe": "CWE-208", "details": ["vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time to First Token). These timing differences caused by matching chunks are significant enough to be recognized and exploited. This issue has been patched in version 0.9.0.", "A timing discrepancy flaw was found in vLLM, where a prefix match on a user prompt can reveal other user prompts. An attacker must have user-level access to the vLLM instance to exploit this vulnerabi"], "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-2025-46570", "package_state": [{"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaiis/vllm-cuda-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaiis/vllm-rocm-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/bootc-amd-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/bootc-aws-nvidia-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/bootc-azure-amd-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/bootc-azure-nvidia-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/bootc-gcp-nvidia-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/bootc-intel-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/bootc-nvidia-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/instructlab-amd-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/instructlab-intel-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/instructlab-nvidia-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"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": "2025-05-29T16:32:42Z", "references": ["https://www.cve.org/CVERecord?id=CVE-2025-46570\nhttps://nvd.nist.gov/vuln/detail/CVE-2025-46570\nhttps://github.com/vllm-project/vllm/commit/77073c77bc2006eb80ea6d5128f076f5e6c6f54f\nhttps://github.com/vllm-project/vllm/pull/17045\nhttps://github.com/vllm-project/vllm/security/advisories/GHSA-4qjh-9fv9-r85r"], "threat_severity": "Low"}