{"id":"CVE-2026-100647","aliases":[],"summary":"vLLM before 0.29.0 CPU Exhaustion via unbounded cache_salt","published_at":"2026-09-26T13:23:18.24Z","modified_at":"2026-10-06T19:50:07Z","products":[],"rating":{"severity":"medium","score":6.9,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N","attack_path":"internet_unauthenticated","user_interaction":false,"malicious":false,"red_hat":"Moderate","vendor_ratings":[{"source":"Red Hat","rating":"Moderate"}]},"fix_available":false,"kev":{"listed":false,"ransomware":false},"public_exploit":false,"exploits":[],"epss":{"score":0.0034799999557435513,"percentile":0.2906999886035919,"date":"2026-11-19T00:00:00Z"},"priority":8.9,"details":"vLLM versions before 0.29.0 contain a denial-of-service vulnerability in the cache_salt parameter accepted on OpenAI-compatible and Anthropic API endpoints, which lacks maximum length validation and is processed on the single EngineCore scheduler thread. Unauthenticated attackers can send HTTP requests with multi-hundred-megabyte salt values that trigger expensive pickle serialization and SHA-256 hashing, stalling the scheduler thread and denying service to all concurrent requests.","affected_stack":[],"affected_other":[{"ecosystem":"CVE","package":"vllm-project/vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.29.0"}]}],"fixed":["0.29.0"],"provider":"cvelistv5","source":"CVE-2026-100647","relation":"self"},{"ecosystem":"NVD","package":"vllm:vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.29.0"}]}],"fixed":["0.29.0"],"provider":"nvd","source":"CVE-2026-100647","relation":"self"}],"product_status":[{"vendor":"Red Hat","product":"Red Hat AI Inference Server","cpe":"cpe:/a:redhat:ai_inference_server:3","status":"affected","packages":["rhaii/vllm-cpu-rhel9","rhaii/vllm-cuda-rhel9","rhaii/vllm-gaudi-rhel9","rhaii/vllm-neuron-rhel9","rhaii/vllm-rocm-rhel9","rhaii/vllm-spyre-rhel9","rhaii/vllm-tpu-rhel9","rhaiis/vllm-cpu-rhel9","rhaiis/vllm-cuda-rhel9","rhaiis/vllm-neuron-rhel9","rhaiis/vllm-rocm-rhel9","rhaiis/vllm-spyre-rhel9","rhaiis/vllm-tpu-rhel9"],"package_count":13,"fixed":[],"advisories":[],"note":"Fix deferred","provider":"redhat-vex","source":"CVE-2026-100647"},{"vendor":"Red Hat","product":"Red Hat Enterprise Linux AI (RHEL AI) 3","cpe":"cpe:/a:redhat:enterprise_linux_ai:3","status":"affected","packages":["rhelai3/bootc-aws-cuda-rhel9","rhelai3/bootc-azure-cuda-rhel9","rhelai3/bootc-azure-rocm-rhel9","rhelai3/bootc-cuda-rhel9","rhelai3/bootc-gaudi-rhel9","rhelai3/bootc-gcp-cuda-rhel9","rhelai3/bootc-rocm-rhel9"],"package_count":7,"fixed":[],"advisories":[],"note":"Fix deferred","provider":"redhat-vex","source":"CVE-2026-100647"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI (RHOAI)","cpe":"cpe:/a:redhat:openshift_ai","status":"affected","packages":["rhoai/odh-kserve-agent-rhel9","rhoai/odh-kserve-controller-rhel9","rhoai/odh-kserve-router-rhel9","rhoai/odh-kserve-storage-initializer-rhel9","rhoai/odh-llm-d-kv-cache-rhel9","rhoai/odh-th-torch-cuda-py312-rhel9","rhoai/odh-vllm-gaudi-rhel9"],"package_count":7,"fixed":[],"advisories":[],"note":"Fix deferred","provider":"redhat-vex","source":"CVE-2026-100647"}],"records":[{"provider":"csaf-bsi","source_id":"WID-SEC-W-2026-3327","relation":"upstream","url":"https://wid.cert-bund.de/portal/wid/securityadvisory?name=WID-SEC-2026-3327","license":"TLP:CLEAR, mirroring permitted","published_at":"2026-09-13T22:00:00Z","modified_at":"2026-11-09T23:00:00Z","summary":"vllm: Mehrere Schwachstellen ermöglichen","details":"Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um Sicherheitsvorkehrungen zu umgehen, Daten zu manipulieren, sensible Informationen offenzulegen oder einen Denial-of-Service-Zustand auszulösen.\n\nOpen Source vLLM ist eine Open-Source-Bibliothek für schnelle und effiziente Inferenz von Large Language Models (LLMs).","severity":[{"type":"BSI","score":"mittel","source":"WID-SEC-W-2026-3327"}],"affected":[],"product_status":[],"references":[{"type":"WEB","url":"https://wid.cert-bund.de/.well-known/csaf/white/2026/wid-sec-w-2026-3327.json"},{"type":"WEB","url":"https://wid.cert-bund.de/portal/wid/securityadvisory?name=WID-SEC-2026-3327"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-3mqx-f33v-vgp9"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-hhv2-872h-628q"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-j682-9xp5-rrf3"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-jcq2-4gch-5qhf"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7v3x-m8mv"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-qff2-492f-9fm4"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-v5gm-qgmv-gc6c"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-wpww-v874-ph2p"},{"type":"WEB","url":"https://access.redhat.com/errata/RHSA-2026:90440"},{"type":"WEB","url":"https://access.redhat.com/errata/RHSA-2026:94721"},{"type":"WEB","url":"https://access.redhat.com/errata/RHSA-2026:94702"},{"type":"WEB","url":"https://access.redhat.com/errata/RHSA-2026:94709"},{"type":"WEB","url":"https://access.redhat.com/errata/RHSA-2026:94738"},{"type":"WEB","url":"https://access.redhat.com/errata/RHSA-2026:94717"},{"type":"WEB","url":"https://access.redhat.com/errata/RHSA-2026:96323"},{"type":"WEB","url":"https://access.redhat.com/errata/RHSA-2026:96333"}]},{"provider":"cvelistv5","source_id":"CVE-2026-100647","relation":"self","url":"https://www.cve.org/CVERecord?id=CVE-2026-100647","license":"CC-BY-4.0","published_at":"2026-09-26T13:23:18.24Z","modified_at":"2026-09-28T18:28:14.772Z","summary":"vLLM before 0.29.0 CPU Exhaustion via unbounded cache_salt","details":"vLLM versions before 0.29.0 contain a denial-of-service vulnerability in the cache_salt parameter accepted on OpenAI-compatible and Anthropic API endpoints, which lacks maximum length validation and is processed on the single EngineCore scheduler thread. Unauthenticated attackers can send HTTP requests with multi-hundred-megabyte salt values that trigger expensive pickle serialization and SHA-256 hashing, stalling the scheduler thread and denying service to all concurrent requests.","severity":[{"type":"CVSS_V4","score":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N","source":"CVE-2026-100647"},{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L","source":"CVE-2026-100647"}],"affected":[{"ecosystem":"CVE","package":"vllm-project/vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.29.0"}]}],"fixed":["0.29.0"],"provider":"cvelistv5","source":"CVE-2026-100647","relation":"self"}],"product_status":[],"references":[{"type":"ADVISORY","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-wpww-v874-ph2p"},{"type":"WEB","url":"https://www.vulncheck.com/advisories/vllm-before-0.29.0-cpu-exhaustion-via-unbounded-cache-salt"}]},{"provider":"nvd","source_id":"CVE-2026-100647","relation":"self","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-100647","severity":[],"affected":[{"ecosystem":"NVD","package":"vllm:vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.29.0"}]}],"fixed":["0.29.0"],"provider":"nvd","source":"CVE-2026-100647","relation":"self"}],"product_status":[],"references":[]},{"provider":"redhat-vex","source_id":"CVE-2026-100647","relation":"self","url":"https://access.redhat.com/security/cve/CVE-2026-100647","license":"CC-BY-4.0","published_at":"2026-09-26T13:23:18.24Z","modified_at":"2026-10-06T19:50:07Z","summary":"vllm: vLLM: Denial of Service via unbounded cache_salt parameter","details":"A flaw was found in vLLM. An unauthenticated remote attacker can cause a Denial of Service (DoS) by sending HTTP requests containing an excessively large cache_salt parameter to exposed API endpoints. Because this input lacks maximum length validation, processing the oversized data consumes excessive CPU resources on the core scheduler thread. This stalling prevents legitimate requests from being processed, resulting in high latency or complete service unavailability for concurrent users.","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L","source":"CVE-2026-100647"},{"type":"Red Hat","score":"Moderate","source":"CVE-2026-100647"}],"affected":[],"product_status":[{"vendor":"Red Hat","product":"Red Hat AI Inference Server","cpe":"cpe:/a:redhat:ai_inference_server:3","status":"affected","packages":["rhaii/vllm-cpu-rhel9","rhaii/vllm-cuda-rhel9","rhaii/vllm-gaudi-rhel9","rhaii/vllm-neuron-rhel9","rhaii/vllm-rocm-rhel9","rhaii/vllm-spyre-rhel9","rhaii/vllm-tpu-rhel9","rhaiis/vllm-cpu-rhel9","rhaiis/vllm-cuda-rhel9","rhaiis/vllm-neuron-rhel9","rhaiis/vllm-rocm-rhel9","rhaiis/vllm-spyre-rhel9","rhaiis/vllm-tpu-rhel9"],"package_count":13,"fixed":[],"advisories":[],"note":"Fix deferred","provider":"redhat-vex","source":"CVE-2026-100647"},{"vendor":"Red Hat","product":"Red Hat Enterprise Linux AI (RHEL AI) 3","cpe":"cpe:/a:redhat:enterprise_linux_ai:3","status":"affected","packages":["rhelai3/bootc-aws-cuda-rhel9","rhelai3/bootc-azure-cuda-rhel9","rhelai3/bootc-azure-rocm-rhel9","rhelai3/bootc-cuda-rhel9","rhelai3/bootc-gaudi-rhel9","rhelai3/bootc-gcp-cuda-rhel9","rhelai3/bootc-rocm-rhel9"],"package_count":7,"fixed":[],"advisories":[],"note":"Fix deferred","provider":"redhat-vex","source":"CVE-2026-100647"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI (RHOAI)","cpe":"cpe:/a:redhat:openshift_ai","status":"affected","packages":["rhoai/odh-kserve-agent-rhel9","rhoai/odh-kserve-controller-rhel9","rhoai/odh-kserve-router-rhel9","rhoai/odh-kserve-storage-initializer-rhel9","rhoai/odh-llm-d-kv-cache-rhel9","rhoai/odh-th-torch-cuda-py312-rhel9","rhoai/odh-vllm-gaudi-rhel9"],"package_count":7,"fixed":[],"advisories":[],"note":"Fix deferred","provider":"redhat-vex","source":"CVE-2026-100647"}],"references":[{"type":"WEB","url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-100647.json"},{"type":"WEB","url":"https://access.redhat.com/security/cve/CVE-2026-100647"},{"type":"WEB","url":"https://bugzilla.redhat.com/show_bug.cgi?id=2541900"},{"type":"WEB","url":"https://www.cve.org/CVERecord?id=CVE-2026-100647"},{"type":"WEB","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-100647"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-wpww-v874-ph2p"},{"type":"WEB","url":"https://www.vulncheck.com/advisories/vllm-before-0.29.0-cpu-exhaustion-via-unbounded-cache-salt"}]}],"references":[{"type":"ADVISORY","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-wpww-v874-ph2p"},{"type":"WEB","url":"https://www.vulncheck.com/advisories/vllm-before-0.29.0-cpu-exhaustion-via-unbounded-cache-salt"},{"type":"WEB","url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-100647.json"},{"type":"WEB","url":"https://access.redhat.com/security/cve/CVE-2026-100647"},{"type":"WEB","url":"https://bugzilla.redhat.com/show_bug.cgi?id=2541900"},{"type":"WEB","url":"https://www.cve.org/CVERecord?id=CVE-2026-100647"},{"type":"WEB","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-100647"}],"sources":[{"provider":"csaf-bsi","source_id":"WID-SEC-W-2026-3327","url":"https://wid.cert-bund.de/portal/wid/securityadvisory?name=WID-SEC-2026-3327","license":"TLP:CLEAR, mirroring permitted","modified_at":"2026-11-09T23:00:00Z","relation":"upstream"},{"provider":"cvelistv5","source_id":"CVE-2026-100647","url":"https://www.cve.org/CVERecord?id=CVE-2026-100647","license":"CC-BY-4.0","modified_at":"2026-09-28T18:28:14.772Z","relation":"self"},{"provider":"nvd","source_id":"CVE-2026-100647","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-100647","relation":"self"},{"provider":"redhat-vex","source_id":"CVE-2026-100647","url":"https://access.redhat.com/security/cve/CVE-2026-100647","license":"CC-BY-4.0","modified_at":"2026-10-06T19:50:07Z","relation":"self"}]}
