{"cve":"CVE-2026-100650","nvd":{"published":"2026-09-26T14:16:47.523","modified":"2026-10-06T19:32:45.337","status":"Analyzed","description":"vLLM through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls (the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed-audio size cap, default 25 MB, and the per-modality --limit-mm-per-prompt item limits). Across four ingress paths — the shared media-acquisition layer (HTTPConnection.get_bytes()/async_get_bytes()), the chat completions audio_url/base64 path, the batch speech runner, and the Rust frontend POST /tokenize route — the server reads the entire HTTP response body, base64-decodes the inline payload, or spawns one fetch/decode task per media part, and only then applies the limit (or, on some paths, never applies it). A remote attacker can therefore cause the API server or batch-runner process to allocate memory and consume outbound bandwidth proportional to an attacker-chosen body size or media item count before the request is rejected, resulting in pre-inference memory and bandwidth exhaustion (denial of service). The chat and batch surfaces require an API key when one is configured; the Rust frontend /tokenize route is unauthenticated by design. There is no code execution or data disclosure impact.","cvss_v4":{"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N","score":7.1},"cvss_v3":{"version":"3.1","vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","score":6.5},"cwes":["CWE-400"],"references":["https://github.com/vllm-project/vllm/commit/752a3a504485790a2e8491cacbb35c137339ad34","https://github.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7v3x-m8mv","https://www.vulncheck.com/advisories/vllm-before-0.29.0-resource-exhaustion-via-unbounded-media-materialization","https://github.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7v3x-m8mv"],"products":["vllm:vllm"],"source":"nvd","synced_at":"2026-10-19T22:56:48.555445741+00:00"},"epss":{"cve":"CVE-2026-100650","score":0.00808,"percentile":0.56591,"date":"2026-10-25"},"kev":null,"osv":[{"id":"PYSEC-2026-4184","url":"https://osv.dev/vulnerability/PYSEC-2026-4184","summary":"","modified":"2026-10-07T10:00:03.384020476Z","packages":[{"ecosystem":"PyPI","name":"vllm","purl":"pkg:pypi/vllm","ranges":["<0.30.0"],"fixed":["0.30.0"]}]}],"attribution":["This product uses the NVD API but is not endorsed or certified by the NVD.","EPSS scores: FIRST Exploit Prediction Scoring System, https://www.first.org/epss","Known exploited vulnerabilities: CISA Known Exploited Vulnerabilities Catalog, https://www.cisa.gov/known-exploited-vulnerabilities-catalog","Package advisories: OSV (https://osv.dev), from the GitHub Advisory Database, PyPA, Go, RustSec and other ecosystem databases, under CC-BY 4.0 or CC0","CVE records: the CVE Program's CVE List (https://www.cve.org), under its terms of use (https://www.cve.org/Legal/TermsOfUse). CVE is a registered trademark of The MITRE Corporation; this product is not affiliated with the CVE Program."]}