Description
SGLang contains a model weight exfiltration vulnerability when no API keys are configured, as SGLang will expose two endpoints that allow a remote attacker to trigger distributed weight broadcasting using NCCL and then triggering data transfer, attackers can exfiltrate all model weights.
Affected products
lmsys: sglang
References3
- github.com/sgl-project/sglang/security/advisories/GHSA-cpqq-22v… Broken Link
- thoughts.apoorvdayal.com/posts/sglang-disclosures/ Third Party AdvisoryMitigation
- thoughts.apoorvdayal.com/posts/sglang-disclosures/ Third Party AdvisoryMitigation
Metrics
- CVSS 3.1
-
7.5
HIGH
Score source: CNA
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N - EPSS — exploit probability
- 1% percentile: 44 · as of 13 November 2026
- CWE
- CWE-306
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.