Description
SGLang through 0.5.22 with the Mooncake disaggregation backend accepts unauthenticated decode registration messages on the Prefill rank ZMQ PULL socket, allowing denial of service. Network-adjacent attackers can send many registrations with unique mooncake_session_id values and large nested-buffer frames to exhaust Prefill memory until the scheduler is OOM-killed.
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/45012 ↗
- https://github.com/sgl-project/sglang/blob/v0.5.22/python/sglang/srt/disaggregation/mooncake/conn.py#L2885-L2935 ↗
- https://github.com/sgl-project/sglang/blob/v0.5.22/python/sglang/srt/disaggregation/mooncake/conn.py#L889-L909 ↗
- https://github.com/sgl-project/sglang/blob/v0.5.22/python/sglang/srt/disaggregation/common/utils.py#L47-L69 ↗
- https://www.vulncheck.com/advisories/sglang-through-0.5.22-memory-exhaustion-via-unauthenticated-mooncake-decode-registrations ↗