CVE-2026-93838SGLang through 0.5.20 Unbounded Memory Allocation via STAGING_REQ chunk_idx
Updated under an hour ago ()
Does this affect you?
It affects sgl-project sglang. Add what you run to find out whether that includes you.
No exploitation reported and no EPSS estimate yet.
Do this next
Free account, 1 product
SGLang versions through 0.5.20 contain an unbounded memory allocation vulnerability in handle_staging_req() that fails to validate chunk_idx from ZMQ STAGING_REQ frames in prefill/decode disaggregation deployments. Attackers with access to the decode engine's internal ZMQ rank port can send a frame with an extremely large chunk_idx value, causing the scheduler to allocate memory until the system runs out and terminates the process.
- CVSS
- 5.9 MEDIUM (v3.1, CNA)CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H
- Weakness (CWE)
- CWE-770
- Known exploited
- Not in CISA's KEV catalog
- EPSS (exploitation in the next 30 days)
- Not loaded for this CVE
- Assigned by
- VulnCheck
- NVD analysis
- Deferred
- Record last updated
- Sep 24, 2026
- First seen by InfoSec Signals
- Oct 9, 2026
Affected products
sgl-project sglang sgl_project:sglang (from the name) | through 0.5.20 | CNA record |
References
- https://github.com/sgl-project/sglang/issues/39764issue-tracking
- https://github.com/sgl-project/sglangproduct
- https://github.com/sgl-project/sglang/blob/v0.5.20/python/sglang/srt/disaggregation/common/staging_handler.py#L781technical-description
- https://github.com/sgl-project/sglang/blob/v0.5.20/python/sglang/srt/disaggregation/common/staging_handler.py#L848-L860technical-description
- https://github.com/sgl-project/sglang/blob/v0.5.20/python/sglang/srt/disaggregation/common/conn.py#L1636-L1640technical-description
- https://www.vulncheck.com/advisories/sglang-through-0.5.20-unbounded-memory-allocation-via-staging-req-chunk-idxthird-party-advisory
The CVE record on cve.org NVD's entry
The CVE record is authoritative. Products marked “from the name” were identified from the CNA's free-text names, not a CPE, and are matched less certainly. This product uses the NVD API but is not endorsed or certified by the NVD.