Description
SGLang through 0.5.22 contains a denial of service vulnerability that allows API clients to abort other users' in-flight generation requests by supplying a short client-controlled rid. Attackers can submit streaming /generate requests with single hex character rids and disconnect, triggering prefix-matching abort logic that terminates all other clients' requests.
Affected products
Version statuses are supplied by the assigning organization. Consult the original record for detailed ranges and platform conditions.
sgl-project sglang
Default version status: unaffected
0 to ≤ 0.5.22affected
pkg:pypi/sglangReferences
- https://github.com/sgl-project/sglang/issues/45002 ↗
- https://github.com/sgl-project/sglang/issues/41474 ↗
- https://github.com/sgl-project/sglang/blob/v0.5.22/python/sglang/srt/managers/scheduler.py#L5458-L5590 ↗
- https://github.com/sgl-project/sglang/blob/v0.5.22/python/sglang/srt/managers/tokenizer_manager.py#L2425-L2436 ↗
- https://github.com/sgl-project/sglang/blob/v0.5.22/python/sglang/srt/managers/tokenizer_manager.py#L2240-L2256 ↗
- https://www.vulncheck.com/advisories/sglang-through-0.5.22-cross-request-abort-via-rid-prefix-matching ↗