Description (CNA)
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 (CNA)
| Vendor / product | Versions |
|---|---|
| sgl-project / sglang | affected 0 through 0.5.22 |
CWE
CWE-770
References
- 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
ADP enrichment
No English description supplied.