{"id":"CVE-2026-109225","published":"2026-10-12T14:17:11.580","lastModified":"2026-10-13T17:17:23.247","description":"SGLang through 0.5.21 contains an unbounded memory allocation vulnerability that allows unauthenticated remote attackers to exhaust memory by uploading oversized files to /v1/audio/transcriptions. Attackers can send concurrent large multipart uploads, which are fully read into memory before validation, to crash the HTTP/tokenizer worker and deny service.","cvssScore":7.5,"cvssSeverity":"HIGH","cvssVector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","cwes":["CWE-770"],"vendors":[],"products":[],"references":[{"url":"https://github.com/sgl-project/sglang","tags":[]},{"url":"https://github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/entrypoints/http_server.py#L1847-L1871","tags":[]},{"url":"https://github.com/sgl-project/sglang/issues/43709","tags":[]},{"url":"https://www.vulncheck.com/advisories/sglang-through-0.5.21-memory-exhaustion-dos-via-v1-audio-transcriptions-upload","tags":[]}],"exploitRefs":[{"url":"https://github.com/sgl-project/sglang","tags":[]},{"url":"https://github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/entrypoints/http_server.py#L1847-L1871","tags":[]},{"url":"https://github.com/sgl-project/sglang/issues/43709","tags":[]}],"hasPoc":true,"ai":null}