Vendor
SGLang Project vulnerabilities
Updated . Rebuilt every hour.
Junglewise Threat Intelligence has tracked 14 vulnerabilities in SGLang Project: 0 in the last 7 days and 8 in the last 90 days, 3 of them critical and 0 exploited in the wild. The most recent, CVE-2026-92972, was published on 17 September 2026. 1 technology has a page of its own.
- Last 7 days
- 0
- Last 90 days
- 8
- Critical, all time
- 3
- Exploited in the wild
- 0
About SGLang Project
Open-source project focused on high-speed serving for large language models.
SGLang Project technologies
Latest SGLang Project vulnerabilities
- CVE-2026-92972: SGLang unauthenticated PUT /route endpoint KV transfer poisoninghighCVSS 8.6EPSS 0.5%
- CVE-2026-15978: SGLang model weight exfiltration via untrusted distributed peer enrollmentinfoCVSS 7.5
- CVE-2026-15977: SGLang credential leakage in server_info endpointinfoCVSS 7.5
- CVE-2026-15976: SGLang insecure pickle deserialization in weight update endpointinfoCVSS 9.8
- CVE-2026-15974: SGLang SSRF and local file read in multimodal chat endpointinfoCVSS 7.5
- CVE-2026-15971: SGLang RCE via eval sandbox escape in dumper subsysteminfoCVSS 9.8
- CVE-2026-15969: SGLang SafeUnpickler bypass RCE in load_lora_adapter_from_tensorsinfoCVSS 9.8
- CVE-2026-14890: SGLang remote code execution in expert-parallel backup subsysteminfoCVSS 9.8
- CVE-2026-10775: sgl-project SGLang denial of service in Cache HandlerlowCVSS 3.6EPSS 0.1%
- CVE-2026-10300: SGLang reachable assertion in LoRA manager scheduler admissionlowCVSS 3.7EPSS 0.4%
- CVE-2026-7304: SGLang RCE via unsafe deserialization in custom logit processorcriticalCVSS 9.8EPSS 0.9%
- CVE-2026-7302: SGLang path traversal in multimodal generation runtimecriticalCVSS 9.1EPSS 0.6%
- CVE-2026-7301: SGLang RCE via insecure pickle deserialization in scheduler ROUTER socketcriticalCVSS 9.8EPSS 0.6%
- CVE-2026-3989: SGLang unsafe pickle deserialization in replay_request_dump.pyhighCVSS 7.8EPSS 0.4%
Most severe SGLang Project vulnerabilities
Exploited in the wild first, then by severity and CVSS score.
- CVE-2026-7304: SGLang RCE via unsafe deserialization in custom logit processorcriticalCVSS 9.8EPSS 0.9%
- CVE-2026-7301: SGLang RCE via insecure pickle deserialization in scheduler ROUTER socketcriticalCVSS 9.8EPSS 0.6%
- CVE-2026-7302: SGLang path traversal in multimodal generation runtimecriticalCVSS 9.1EPSS 0.6%
- CVE-2026-92972: SGLang unauthenticated PUT /route endpoint KV transfer poisoninghighCVSS 8.6EPSS 0.5%
- CVE-2026-3989: SGLang unsafe pickle deserialization in replay_request_dump.pyhighCVSS 7.8EPSS 0.4%
- CVE-2026-10300: SGLang reachable assertion in LoRA manager scheduler admissionlowCVSS 3.7EPSS 0.4%
- CVE-2026-10775: sgl-project SGLang denial of service in Cache HandlerlowCVSS 3.6EPSS 0.1%
- CVE-2026-15976: SGLang insecure pickle deserialization in weight update endpointinfoCVSS 9.8
- CVE-2026-15971: SGLang RCE via eval sandbox escape in dumper subsysteminfoCVSS 9.8
- CVE-2026-15969: SGLang SafeUnpickler bypass RCE in load_lora_adapter_from_tensorsinfoCVSS 9.8
Vulnerabilities per week
The last 13 weeks, by the week each vulnerability was published.
| Week of | Bar | Vulns | Critical |
|---|---|---|---|
| 29 Jun 2026 | 0 | 0 | |
| 6 Jul 2026 | 0 | 0 | |
| 13 Jul 2026 | 1 | 0 | |
| 20 Jul 2026 | 0 | 0 | |
| 27 Jul 2026 | 6 | 0 | |
| 3 Aug 2026 | 0 | 0 | |
| 10 Aug 2026 | 0 | 0 | |
| 17 Aug 2026 | 0 | 0 | |
| 24 Aug 2026 | 0 | 0 | |
| 31 Aug 2026 | 0 | 0 | |
| 7 Sep 2026 | 0 | 0 | |
| 14 Sep 2026 | 1 | 0 | |
| 21 Sep 2026 | 0 | 0 |
How this is built
Junglewise Threat Intelligence collects vulnerabilities from NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories, and matches each one to the technologies and vendors it affects. Dates are the date a vulnerability was published, in UTC.
The pages are rebuilt from the database every hour. Frozen weekly and monthly reports never change once published, so they can be cited.
Use this data
The same data is at https://junglewise.ai/threats/vendors/sglang-project.json, for scripts and language models. It is free to reuse under CC BY 4.0 with a link back to this page.
Cite as: Junglewise Threat Intelligence, "SGLang Project vulnerabilities", https://junglewise.ai/threats/vendors/sglang-project, 26 September 2026.