{"api_version":"1","generated_at":"2026-10-06T02:03:39+00:00","cve":"CVE-2026-105760","urls":{"html":"https://cve.report/CVE-2026-105760","api":"https://cve.report/api/cve/CVE-2026-105760.json","docs":"https://cve.report/api","cve_org":"https://www.cve.org/CVERecord?id=CVE-2026-105760","nvd":"https://nvd.nist.gov/vuln/detail/CVE-2026-105760"},"summary":{"title":"vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion","description":"vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level media_io_kwargs field to select the GLMGA video backend and supply large values for the fps and max_frames options without a strict work ceiling. GLMGA constructs and deduplicates an attacker-sized pre-decode frame-index list, allowing a compact request and tiny valid video to consume disproportionate CPU time and memory in the shared media-loading executor. This issue is fixed in version 0.30.0.","state":"PUBLISHED","assigner":"GitHub_M","published_at":"2026-10-05 23:17:02","updated_at":"2026-10-05 23:17:02"},"problem_types":["CWE-400","CWE-400 CWE-400: Uncontrolled Resource Consumption"],"metrics":[{"version":"3.1","source":"security-advisories@github.com","type":"Secondary","score":"5.3","severity":"MEDIUM","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L","data":{"version":"3.1","vectorString":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L","baseScore":5.3,"baseSeverity":"MEDIUM","attackVector":"NETWORK","attackComplexity":"LOW","privilegesRequired":"NONE","userInteraction":"NONE","scope":"UNCHANGED","confidentialityImpact":"NONE","integrityImpact":"NONE","availabilityImpact":"LOW"}},{"version":"3.1","source":"CNA","type":"DECLARED","score":"5.3","severity":"MEDIUM","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L","data":{"attackComplexity":"LOW","attackVector":"NETWORK","availabilityImpact":"LOW","baseScore":5.3,"baseSeverity":"MEDIUM","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:L","version":"3.1"}}],"references":[{"url":"https://github.com/vllm-project/vllm/releases/tag/v0.30.0","name":"https://github.com/vllm-project/vllm/releases/tag/v0.30.0","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-58v5-2m8f-94pr","name":"https://github.com/vllm-project/vllm/security/advisories/GHSA-58v5-2m8f-94pr","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://github.com/vllm-project/vllm/pull/54935","name":"https://github.com/vllm-project/vllm/pull/54935","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://github.com/vllm-project/vllm/commit/8b6de0eb9a09ef53f20cf06bd4d17ee264b9c2a7","name":"https://github.com/vllm-project/vllm/commit/8b6de0eb9a09ef53f20cf06bd4d17ee264b9c2a7","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-105760","name":"CVE Program record","refsource":"CVE.ORG","tags":["canonical"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-105760","name":"NVD vulnerability detail","refsource":"NVD","tags":["canonical","analysis"]}],"affected":[{"source":"CNA","vendor":"vllm-project","product":"vllm","version":"affected >= 0.23.0rc2, < 0.30.0","platforms":[]}],"timeline":[],"solutions":[],"workarounds":[],"exploits":[],"credits":[],"nvd_cpes":[],"vendor_comments":[],"enrichments":{"kev":null,"epss":null,"legacy_qids":[]},"source_records":{"cve_program":{"containers":{"cna":{"affected":[{"product":"vllm","vendor":"vllm-project","versions":[{"status":"affected","version":">= 0.23.0rc2, < 0.30.0"}]}],"descriptions":[{"lang":"en","value":"vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level media_io_kwargs field to select the GLMGA video backend and supply large values for the fps and max_frames options without a strict work ceiling. GLMGA constructs and deduplicates an attacker-sized pre-decode frame-index list, allowing a compact request and tiny valid video to consume disproportionate CPU time and memory in the shared media-loading executor. This issue is fixed in version 0.30.0."}],"metrics":[{"cvssV3_1":{"attackComplexity":"LOW","attackVector":"NETWORK","availabilityImpact":"LOW","baseScore":5.3,"baseSeverity":"MEDIUM","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:L","version":"3.1"}}],"problemTypes":[{"descriptions":[{"cweId":"CWE-400","description":"CWE-400: Uncontrolled Resource Consumption","lang":"en","type":"CWE"}]}],"providerMetadata":{"dateUpdated":"2026-10-05T23:01:54.972Z","orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","shortName":"GitHub_M"},"references":[{"name":"https://github.com/vllm-project/vllm/security/advisories/GHSA-58v5-2m8f-94pr","tags":["x_refsource_CONFIRM"],"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-58v5-2m8f-94pr"},{"name":"https://github.com/vllm-project/vllm/pull/54935","tags":["x_refsource_MISC"],"url":"https://github.com/vllm-project/vllm/pull/54935"},{"name":"https://github.com/vllm-project/vllm/commit/8b6de0eb9a09ef53f20cf06bd4d17ee264b9c2a7","tags":["x_refsource_MISC"],"url":"https://github.com/vllm-project/vllm/commit/8b6de0eb9a09ef53f20cf06bd4d17ee264b9c2a7"},{"name":"https://github.com/vllm-project/vllm/releases/tag/v0.30.0","tags":["x_refsource_MISC"],"url":"https://github.com/vllm-project/vllm/releases/tag/v0.30.0"}],"source":{"advisory":"GHSA-58v5-2m8f-94pr","discovery":"UNKNOWN"},"title":"vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion"}},"cveMetadata":{"assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","assignerShortName":"GitHub_M","cveId":"CVE-2026-105760","datePublished":"2026-10-05T23:01:54.972Z","dateReserved":"2026-10-05T19:11:07.948Z","dateUpdated":"2026-10-05T23:01:54.972Z","state":"PUBLISHED"},"dataType":"CVE_RECORD","dataVersion":"5.2"},"nvd":{"publishedDate":"2026-10-05 23:17:02","lastModifiedDate":"2026-10-05 23:17:02","problem_types":["CWE-400","CWE-400 CWE-400: Uncontrolled Resource Consumption"],"metrics":{"cvssMetricV31":[{"source":"security-advisories@github.com","type":"Secondary","cvssData":{"version":"3.1","vectorString":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L","baseScore":5.3,"baseSeverity":"MEDIUM","attackVector":"NETWORK","attackComplexity":"LOW","privilegesRequired":"NONE","userInteraction":"NONE","scope":"UNCHANGED","confidentialityImpact":"NONE","integrityImpact":"NONE","availabilityImpact":"LOW"},"exploitabilityScore":3.9,"impactScore":1.4}]},"configurations":[]},"legacy_mitre":{"record":{"CveYear":"2026","CveId":"105760","Ordinal":"1","Title":"vLLM: GLMGA video sampling permits request-driven CPU and memory","CVE":"CVE-2026-105760","Year":"2026"},"notes":[{"CveYear":"2026","CveId":"105760","Ordinal":"1","NoteData":"vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level media_io_kwargs field to select the GLMGA video backend and supply large values for the fps and max_frames options without a strict work ceiling. GLMGA constructs and deduplicates an attacker-sized pre-decode frame-index list, allowing a compact request and tiny valid video to consume disproportionate CPU time and memory in the shared media-loading executor. This issue is fixed in version 0.30.0.","Type":"Description","Title":"vLLM: GLMGA video sampling permits request-driven CPU and memory"}]}}}