Description
SGLang through 0.5.22 with the Mooncake disaggregation backend contains an uncontrolled memory allocation vulnerability in handle_staging_rsp() that lets unauthenticated network-adjacent attackers exhaust Prefill memory. Attackers can obtain the rank address from the /route endpoint and send STAGING_RSP messages with huge chunk_idx values under fresh room IDs, causing the scheduler to be OOM-killed.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| sgl-project | sglang | ≤ 0.5.22 | — |
References
- https://github.com/sgl-project/sglang/issues/45014 issue-tracking
- https://github.com/sgl-project/sglang/blob/v0.5.22/python/sglang/srt/disaggregation/common/staging_handler.py#L505-L548 technical-description
- https://github.com/sgl-project/sglang/blob/v0.5.22/python/sglang/srt/disaggregation/mooncake/conn.py#L2885-L2935 technical-description
- VulnCheck Advisory: SGLang through 0.5.22 Memory Exhaustion via Mooncake STAGING_RSP chunk_idx third-party-advisory