{"id":"CVE-2026-105759","aliases":["GHSA-5fj9-pfhr-6j48","PYSEC-2026-4325"],"summary":"vLLM: Unbounded Prometheus label cardinality from attacker-controlled HTTP method tokens in the vLLM Rust frontend metrics middleware (unauthenticated denial of service)","published_at":"2026-10-05T22:58:01.362Z","modified_at":"2026-10-23T19:00:39.87539Z","products":[],"rating":{"severity":"high","score":7.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","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":0.004110000096261501,"percentile":0.3613699972629547,"date":"2026-11-19T00:00:00Z"},"priority":9.5,"details":"vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the Rust frontend's track_http_metrics middleware records the raw HTTP method token as a Prometheus label for requests reaching registered routes. An unauthenticated attacker can send unique arbitrary method tokens to unguarded routes such as /tokenize, causing Prometheus's Family::get_or_create function to permanently create counter and histogram label sets. Those label sets increase process memory usage and enlarge the /metrics response until the service or monitoring path is exhausted. This issue is fixed in version 0.30.0.","affected_stack":[],"affected_other":[{"ecosystem":"CVE","package":"vllm-project/vllm","versions":["< 0.30.0"],"provider":"cvelistv5","source":"CVE-2026-105759","relation":"self"},{"ecosystem":"NVD","package":"vllm:vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.30.0"}]}],"fixed":["0.30.0"],"provider":"nvd","source":"CVE-2026-105759","relation":"self"},{"ecosystem":"PyPI","package":"vllm","purl":"pkg:pypi/vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.30.0"}]}],"versions":["0.0.1","0.1.0","0.1.1","0.1.2","0.1.3","0.1.4","0.1.5","0.1.6","0.1.7","0.10.0","0.10.1","0.10.1.1","0.10.2","0.11.0","0.11.1","0.11.2","0.12.0","0.13.0","0.14.0","0.14.1","0.15.0","0.15.1","0.16.0","0.17.0","0.17.1","0.18.0","0.18.1","0.19.0","0.19.1","0.2.0","0.2.1","0.2.1.post1","0.2.2","0.2.3","0.2.4","0.2.5","0.2.6","0.2.7","0.20.0","0.20.1","0.20.2","0.21.0","0.22.0","0.22.1","0.23.0","0.24.0","0.25.0","0.25.1","0.26.0","0.27.0","0.27.1","0.28.0","0.29.0","0.3.0","0.3.1","0.3.2","0.3.3","0.4.0","0.4.0.post1","0.4.1","0.4.2","0.4.3","0.5.0","0.5.0.post1","0.5.1","0.5.2","0.5.3","0.5.3.post1","0.5.4","0.5.5","0.6.0","0.6.1","0.6.1.post1","0.6.1.post2","0.6.2","0.6.3","0.6.3.post1","0.6.4","0.6.4.post1","0.6.5","0.6.6","0.6.6.post1","0.7.0","0.7.1","0.7.2","0.7.3","0.8.0","0.8.1","0.8.2","0.8.3","0.8.4","0.8.5","0.8.5.post1","0.9.0","0.9.0.1","0.9.1","0.9.2"],"fixed":["0.30.0"],"provider":"osv","source":"PYSEC-2026-4325","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-2026-105759"},{"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-2026-105759"},{"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-2026-105759"}],"records":[{"provider":"csaf-bsi","source_id":"WID-SEC-W-2026-3754","relation":"upstream","url":"https://wid.cert-bund.de/portal/wid/securityadvisory?name=WID-SEC-2026-3754","license":"TLP:CLEAR, mirroring permitted","published_at":"2026-10-05T22:00:00Z","modified_at":"2026-10-05T22:00:00Z","summary":"vllm: Mehrere Schwachstellen ermöglichen Denial of Service","details":"Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um einen Denial of Service Angriff durchzuführen.\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-2026-3754"}],"affected":[],"product_status":[],"references":[{"type":"WEB","url":"https://wid.cert-bund.de/.well-known/csaf/white/2026/wid-sec-w-2026-3754.json"},{"type":"WEB","url":"https://wid.cert-bund.de/portal/wid/securityadvisory?name=WID-SEC-2026-3754"},{"type":"WEB","url":"https://github.com/advisories/GHSA-x6mc-67gf-chw4"},{"type":"WEB","url":"https://github.com/advisories/GHSA-ph3r-5jfg-f84f"},{"type":"WEB","url":"https://github.com/advisories/GHSA-58v5-2m8f-94pr"},{"type":"WEB","url":"https://github.com/advisories/GHSA-2823-qmq8-rwvj"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-5fj9-pfhr-6j48"}]},{"provider":"cvelistv5","source_id":"CVE-2026-105759","relation":"self","url":"https://www.cve.org/CVERecord?id=CVE-2026-105759","license":"CC-BY-4.0","published_at":"2026-10-05T22:58:01.362Z","modified_at":"2026-10-06T17:56:44.425Z","summary":"vLLM: Unbounded Prometheus label cardinality from attacker-controlled HTTP method tokens in the vLLM Rust frontend metrics middleware (unauthenticated denial of service)","details":"vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the Rust frontend's track_http_metrics middleware records the raw HTTP method token as a Prometheus label for requests reaching registered routes. An unauthenticated attacker can send unique arbitrary method tokens to unguarded routes such as /tokenize, causing Prometheus's Family::get_or_create function to permanently create counter and histogram label sets. Those label sets increase process memory usage and enlarge the /metrics response until the service or monitoring path is exhausted. This issue is fixed in version 0.30.0.","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H","source":"CVE-2026-105759"}],"affected":[{"ecosystem":"CVE","package":"vllm-project/vllm","versions":["< 0.30.0"],"provider":"cvelistv5","source":"CVE-2026-105759","relation":"self"}],"product_status":[],"references":[{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-5fj9-pfhr-6j48"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/pull/56058"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/commit/3735c2d5f5248259482b9045c34fb7a8a3892352"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/releases/tag/v0.30.0"}]},{"provider":"nvd","source_id":"CVE-2026-105759","relation":"self","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-105759","severity":[],"affected":[{"ecosystem":"NVD","package":"vllm:vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.30.0"}]}],"fixed":["0.30.0"],"provider":"nvd","source":"CVE-2026-105759","relation":"self"}],"product_status":[],"references":[]},{"provider":"osv","source_id":"PYSEC-2026-4325","relation":"self","url":"https://osv.dev/vulnerability/PYSEC-2026-4325","license":"CC-BY-4.0","published_at":"2026-10-05T23:17:02.76Z","modified_at":"2026-10-23T19:00:39.87539Z","details":"vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the Rust frontend's track_http_metrics middleware records the raw HTTP method token as a Prometheus label for requests reaching registered routes. An unauthenticated attacker can send unique arbitrary method tokens to unguarded routes such as /tokenize, causing Prometheus's Family::get_or_create function to permanently create counter and histogram label sets. Those label sets increase process memory usage and enlarge the /metrics response until the service or monitoring path is exhausted. This issue is fixed in version 0.30.0.","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","source":"PYSEC-2026-4325"}],"affected":[{"ecosystem":"PyPI","package":"vllm","purl":"pkg:pypi/vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.30.0"}]}],"versions":["0.0.1","0.1.0","0.1.1","0.1.2","0.1.3","0.1.4","0.1.5","0.1.6","0.1.7","0.10.0","0.10.1","0.10.1.1","0.10.2","0.11.0","0.11.1","0.11.2","0.12.0","0.13.0","0.14.0","0.14.1","0.15.0","0.15.1","0.16.0","0.17.0","0.17.1","0.18.0","0.18.1","0.19.0","0.19.1","0.2.0","0.2.1","0.2.1.post1","0.2.2","0.2.3","0.2.4","0.2.5","0.2.6","0.2.7","0.20.0","0.20.1","0.20.2","0.21.0","0.22.0","0.22.1","0.23.0","0.24.0","0.25.0","0.25.1","0.26.0","0.27.0","0.27.1","0.28.0","0.29.0","0.3.0","0.3.1","0.3.2","0.3.3","0.4.0","0.4.0.post1","0.4.1","0.4.2","0.4.3","0.5.0","0.5.0.post1","0.5.1","0.5.2","0.5.3","0.5.3.post1","0.5.4","0.5.5","0.6.0","0.6.1","0.6.1.post1","0.6.1.post2","0.6.2","0.6.3","0.6.3.post1","0.6.4","0.6.4.post1","0.6.5","0.6.6","0.6.6.post1","0.7.0","0.7.1","0.7.2","0.7.3","0.8.0","0.8.1","0.8.2","0.8.3","0.8.4","0.8.5","0.8.5.post1","0.9.0","0.9.0.1","0.9.1","0.9.2"],"fixed":["0.30.0"],"provider":"osv","source":"PYSEC-2026-4325","relation":"self"}],"product_status":[],"references":[{"type":"ADVISORY","url":"https://github.com/vllm-project/vllm/releases/tag/v0.30.0"},{"type":"FIX","url":"https://github.com/vllm-project/vllm/commit/3735c2d5f5248259482b9045c34fb7a8a3892352"},{"type":"FIX","url":"https://github.com/vllm-project/vllm/pull/56058"},{"type":"EVIDENCE","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-5fj9-pfhr-6j48"}]},{"provider":"redhat-vex","source_id":"CVE-2026-105759","relation":"self","url":"https://access.redhat.com/security/cve/CVE-2026-105759","license":"CC-BY-4.0","published_at":"2026-10-05T22:58:01.362Z","modified_at":"2026-10-16T20:50:11Z","summary":"vllm: vLLM: Denial of service via arbitrary HTTP method tokens in metrics tracking","details":"A flaw was found in vLLM. An unauthenticated remote attacker can cause a denial of service (DoS) by sending requests with arbitrary, non-standard HTTP method names to unguarded server routes. Because the metrics tracking middleware records raw request methods into monitoring labels without validation or size limits, the server permanently stores entries for each unique method received. Over time, this unbounded memory consumption can exhaust system resources and crash the process.","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H","source":"CVE-2026-105759"},{"type":"Red Hat","score":"Moderate","source":"CVE-2026-105759"}],"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-2026-105759"},{"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-2026-105759"},{"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-2026-105759"}],"references":[{"type":"WEB","url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-105759.json"},{"type":"WEB","url":"https://access.redhat.com/security/cve/CVE-2026-105759"},{"type":"WEB","url":"https://bugzilla.redhat.com/show_bug.cgi?id=2546208"},{"type":"WEB","url":"https://www.cve.org/CVERecord?id=CVE-2026-105759"},{"type":"WEB","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-105759"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/commit/3735c2d5f5248259482b9045c34fb7a8a3892352"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/pull/56058"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/releases/tag/v0.30.0"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-5fj9-pfhr-6j48"}]}],"references":[{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-5fj9-pfhr-6j48"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/pull/56058"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/commit/3735c2d5f5248259482b9045c34fb7a8a3892352"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/releases/tag/v0.30.0"},{"type":"WEB","url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-105759.json"},{"type":"WEB","url":"https://access.redhat.com/security/cve/CVE-2026-105759"},{"type":"WEB","url":"https://bugzilla.redhat.com/show_bug.cgi?id=2546208"},{"type":"WEB","url":"https://www.cve.org/CVERecord?id=CVE-2026-105759"},{"type":"WEB","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-105759"}],"sources":[{"provider":"csaf-bsi","source_id":"WID-SEC-W-2026-3754","url":"https://wid.cert-bund.de/portal/wid/securityadvisory?name=WID-SEC-2026-3754","license":"TLP:CLEAR, mirroring permitted","modified_at":"2026-10-05T22:00:00Z","relation":"upstream"},{"provider":"cvelistv5","source_id":"CVE-2026-105759","url":"https://www.cve.org/CVERecord?id=CVE-2026-105759","license":"CC-BY-4.0","modified_at":"2026-10-06T17:56:44.425Z","relation":"self"},{"provider":"nvd","source_id":"CVE-2026-105759","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-105759","relation":"self"},{"provider":"osv","source_id":"PYSEC-2026-4325","url":"https://osv.dev/vulnerability/PYSEC-2026-4325","license":"CC-BY-4.0","modified_at":"2026-10-23T19:00:39.87539Z","relation":"self"},{"provider":"redhat-vex","source_id":"CVE-2026-105759","url":"https://access.redhat.com/security/cve/CVE-2026-105759","license":"CC-BY-4.0","modified_at":"2026-10-16T20:50:11Z","relation":"self"}]}
