# SGLang Project vulnerabilities Source: https://junglewise.ai/threats/vendors/sglang-project Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats Updated: 12 November 2026, 03:07 UTC. Rebuilt every hour. Data: https://junglewise.ai/threats/vendors/sglang-project.json License: CC BY 4.0 with a link back Junglewise Threat Intelligence has tracked 24 vulnerabilities in SGLang Project: 0 in the last 7 days and 11 in the last 90 days, 3 of them critical and 0 exploited in the wild. The most recent, CVE-2026-112270, was published on 19 October 2026. 8 vulnerabilities in the last four weeks, up 167% on the four before (3). 1 technology has a page of its own. ## Counts - Last 7 days: 0 - Last 30 days: 5 - Last 90 days: 11 - All time: 24 (3 critical, 0 exploited in the wild) ## About SGLang Project Open-source project focused on high-speed serving for large language models. ## Latest SGLang Project vulnerabilities - [CVE-2026-112270: SGLang uncontrolled memory allocation in Mooncake disaggregation backend](https://junglewise.ai/threats/cve-2026-112270-sglang-through-0-5-22-with-the-mooncake-disaggregation-backend) (medium, CVSS 6.5, published 19 Oct 2026) - [CVE-2026-112269: SGLang Mooncake disaggregation backend unauthenticated denial of service](https://junglewise.ai/threats/cve-2026-112269-sglang-through-0-5-22-with-the-mooncake-disaggregation-backend) (medium, CVSS 6.5, published 19 Oct 2026) - [CVE-2026-112267: SGLang server-side request forgery in prefill/decode disaggregation](https://junglewise.ai/threats/cve-2026-112267-sglang-through-0-5-22-in-prefill-decode-disaggregation-mode) (medium, CVSS 6.5, published 19 Oct 2026) - [CVE-2026-111392: SGLang cache poisoning via untrusted mm_hashes in multimodal prefix cache](https://junglewise.ai/threats/cve-2026-111392-sglang-through-0-5-21-trusts-caller-supplied-mm-hashes-values-as) (medium, CVSS 4.8, published 16 Oct 2026) - [CVE-2026-111391: SGLang code injection in _evaluate_filter()](https://junglewise.ai/threats/cve-2026-111391-sglang-0-5-10-through-0-5-22-contains-a-code-injection) (high, CVSS 8.1, published 16 Oct 2026) - [CVE-2026-109229: SGLang denial of service via disabled image decompression protection](https://junglewise.ai/threats/cve-2026-109229-sglang-through-0-5-21-contains-a-denial-of-service-vulnerability) (high, CVSS 7.5, published 12 Oct 2026) - [CVE-2026-109228: SGLang resource budget bypass in GLM-V video processing](https://junglewise.ai/threats/cve-2026-109228-sglang-through-0-5-21-contains-a-resource-budget-bypass) (high, CVSS 7.5, published 12 Oct 2026) - [CVE-2026-109226: SGLang decompression amplification in load_audio](https://junglewise.ai/threats/cve-2026-109226-sglang-through-0-5-21-contains-a-decompression-amplification) (high, CVSS 7.5, published 12 Oct 2026) - [CVE-2026-93838: SGLang unbounded memory allocation in handle_staging_req](https://junglewise.ai/threats/cve-2026-93838-sglang-versions-through-0-5-20-contain-an-unbounded-memory) (medium, CVSS 5.9, published 18 Sep 2026) - [CVE-2026-93688: SGLang denial of service in prefill/decode disaggregation mode with Mooncake backend](https://junglewise.ai/threats/cve-2026-93688-sglang-through-0-5-19-in-prefill-decode-disaggregation-mode-with) (high, CVSS 7.5, published 18 Sep 2026) - [CVE-2026-92972: SGLang unauthenticated PUT /route endpoint KV transfer poisoning](https://junglewise.ai/threats/cve-2026-92972-sglang-unauthenticated-put-route-endpoint-kv-transfer-poisoning) (high, CVSS 8.6, published 17 Sep 2026) - [CVE-2026-15978: SGLang model weight exfiltration via untrusted distributed peer enrollment](https://junglewise.ai/threats/cve-2026-15978-sglang-model-weight-exfiltration-via-untrusted-distributed-peer) (info, CVSS 7.5, published 30 Jul 2026) - [CVE-2026-15977: SGLang credential leakage in server_info endpoint](https://junglewise.ai/threats/cve-2026-15977-sglang-credential-leakage-in-server-info-endpoint) (info, CVSS 7.5, published 30 Jul 2026) - [CVE-2026-15976: SGLang insecure pickle deserialization in weight update endpoint](https://junglewise.ai/threats/cve-2026-15976-sglang-insecure-pickle-deserialization-in-weight-update-endpoint) (info, CVSS 9.8, published 30 Jul 2026) - [CVE-2026-15974: SGLang SSRF and local file read in multimodal chat endpoint](https://junglewise.ai/threats/cve-2026-15974-sglang-ssrf-and-local-file-read-in-multimodal-chat-endpoint) (info, CVSS 7.5, published 30 Jul 2026) - [CVE-2026-15971: SGLang RCE via eval sandbox escape in dumper subsystem](https://junglewise.ai/threats/cve-2026-15971-sglang-rce-via-eval-sandbox-escape-in-dumper-subsystem) (info, CVSS 9.8, published 30 Jul 2026) - [CVE-2026-15969: SGLang SafeUnpickler bypass RCE in load_lora_adapter_from_tensors](https://junglewise.ai/threats/cve-2026-15969-sglang-safeunpickler-bypass-rce-in-load-lora-adapter-from-tensors) (info, CVSS 9.8, published 30 Jul 2026) - [CVE-2026-14890: SGLang remote code execution in expert-parallel backup subsystem](https://junglewise.ai/threats/cve-2026-14890-sglang-remote-code-execution-in-expert-parallel-backup-subsystem) (info, CVSS 9.8, published 16 Jul 2026) - [CVE-2026-10775: sgl-project SGLang denial of service in Cache Handler](https://junglewise.ai/threats/cve-2026-10775-sgl-project-sglang-denial-of-service-in-cache-handler) (low, CVSS 3.6, published 3 Jun 2026) - [CVE-2026-10300: SGLang reachable assertion in LoRA manager scheduler admission](https://junglewise.ai/threats/cve-2026-10300-sglang-reachable-assertion-in-lora-manager-scheduler-admission) (low, CVSS 3.7, published 1 Jun 2026) - [CVE-2026-7304: SGLang RCE via unsafe deserialization in custom logit processor](https://junglewise.ai/threats/cve-2026-7304-sglang-rce-via-unsafe-deserialization-in-custom-logit-processor) (critical, CVSS 9.8, published 18 May 2026) - [CVE-2026-7302: SGLang path traversal in multimodal generation runtime](https://junglewise.ai/threats/cve-2026-7302-sglang-path-traversal-in-multimodal-generation-runtime) (critical, CVSS 9.1, published 18 May 2026) - [CVE-2026-7301: SGLang RCE via insecure pickle deserialization in scheduler ROUTER socket](https://junglewise.ai/threats/cve-2026-7301-sglang-rce-via-insecure-pickle-deserialization-in-scheduler-router) (critical, CVSS 9.8, published 18 May 2026) - [CVE-2026-3989: SGLang unsafe pickle deserialization in replay_request_dump.py](https://junglewise.ai/threats/cve-2026-3989-sglang-unsafe-pickle-deserialization-in-replay-request-dump-py) (high, CVSS 7.8, published 12 Mar 2026) ## Most severe SGLang Project vulnerabilities - [CVE-2026-7304: SGLang RCE via unsafe deserialization in custom logit processor](https://junglewise.ai/threats/cve-2026-7304-sglang-rce-via-unsafe-deserialization-in-custom-logit-processor) (critical, CVSS 9.8, published 18 May 2026) - [CVE-2026-7301: SGLang RCE via insecure pickle deserialization in scheduler ROUTER socket](https://junglewise.ai/threats/cve-2026-7301-sglang-rce-via-insecure-pickle-deserialization-in-scheduler-router) (critical, CVSS 9.8, published 18 May 2026) - [CVE-2026-7302: SGLang path traversal in multimodal generation runtime](https://junglewise.ai/threats/cve-2026-7302-sglang-path-traversal-in-multimodal-generation-runtime) (critical, CVSS 9.1, published 18 May 2026) - [CVE-2026-92972: SGLang unauthenticated PUT /route endpoint KV transfer poisoning](https://junglewise.ai/threats/cve-2026-92972-sglang-unauthenticated-put-route-endpoint-kv-transfer-poisoning) (high, CVSS 8.6, published 17 Sep 2026) - [CVE-2026-111391: SGLang code injection in _evaluate_filter()](https://junglewise.ai/threats/cve-2026-111391-sglang-0-5-10-through-0-5-22-contains-a-code-injection) (high, CVSS 8.1, published 16 Oct 2026) - [CVE-2026-3989: SGLang unsafe pickle deserialization in replay_request_dump.py](https://junglewise.ai/threats/cve-2026-3989-sglang-unsafe-pickle-deserialization-in-replay-request-dump-py) (high, CVSS 7.8, published 12 Mar 2026) - [CVE-2026-93688: SGLang denial of service in prefill/decode disaggregation mode with Mooncake backend](https://junglewise.ai/threats/cve-2026-93688-sglang-through-0-5-19-in-prefill-decode-disaggregation-mode-with) (high, CVSS 7.5, published 18 Sep 2026) - [CVE-2026-109228: SGLang resource budget bypass in GLM-V video processing](https://junglewise.ai/threats/cve-2026-109228-sglang-through-0-5-21-contains-a-resource-budget-bypass) (high, CVSS 7.5, published 12 Oct 2026) - [CVE-2026-109226: SGLang decompression amplification in load_audio](https://junglewise.ai/threats/cve-2026-109226-sglang-through-0-5-21-contains-a-decompression-amplification) (high, CVSS 7.5, published 12 Oct 2026) - [CVE-2026-109229: SGLang denial of service via disabled image decompression protection](https://junglewise.ai/threats/cve-2026-109229-sglang-through-0-5-21-contains-a-denial-of-service-vulnerability) (high, CVSS 7.5, published 12 Oct 2026) ## Vulnerabilities per week 8 vulnerabilities in the last four weeks, up 167% on the four before (3). | Week of | Vulns | Critical | Exploited | | --- | --- | --- | --- | | 17 Aug 2026 | 0 | 0 | 0 | | 24 Aug 2026 | 0 | 0 | 0 | | 31 Aug 2026 | 0 | 0 | 0 | | 7 Sep 2026 | 0 | 0 | 0 | | 14 Sep 2026 | 3 | 0 | 0 | | 21 Sep 2026 | 0 | 0 | 0 | | 28 Sep 2026 | 0 | 0 | 0 | | 5 Oct 2026 | 0 | 0 | 0 | | 12 Oct 2026 | 5 | 0 | 0 | | 19 Oct 2026 | 3 | 0 | 0 | | 26 Oct 2026 | 0 | 0 | 0 | | 2 Nov 2026 | 0 | 0 | 0 | | 9 Nov 2026 | 0 | 0 | 0 | ## SGLang Project technologies - [SGLang Project SGLang](https://junglewise.ai/threats/technologies/sglang): 26 vulnerabilities ## Sources NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories. Rebuilt every hour. Cite as: Junglewise Threat Intelligence, "SGLang Project vulnerabilities", https://junglewise.ai/threats/vendors/sglang-project, 12 November 2026.