UTC

SGLang

By SGLang. 18 published vulnerabilities.

Advisories
18
Critical
10
Exploited in the wild
None listed
Latest
2026-07-30
Packages it ships
Vulnerabilities
SeverityVulnerabilityPublishedFixed in
HighSGLang 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…CVE-2026-159782026-07-30See advisory
HighSGLang contains a credential leakage vulnerability in the /server_info endpoint, which will return API keys and SSL keyfile information when only the --admin-api-key is configured.CVE-2026-159772026-07-30See advisory
CriticalSGLang contains a RCE vulnerability when attempting to load model weights from a HuggingFace repository, specifically within the /updateweightsfromdisk, where torch.load(..., weightsonly=False) fallback enables pickle deserialization of…CVE-2026-159762026-07-30See advisory
MediumSGLang contains an SSRF and local file read in the multimodal generation endpoint /v1/chat/completions due to unsanitized image_url, allowing access to internal metadata, secrets, and services.CVE-2026-159742026-07-30See advisory
CriticalSGLang contains an RCE vulnerability when the optional dumper subsystem is enabled, allowing for a sandbox escape when DUMPERSERVERPORT is set, enabling code execution on inference requests.CVE-2026-159712026-07-30See advisory
CriticalSGLang contains an unauthenticated RCE in /loadloraadapterfromtensors via bypass of SafeUnpickler’s incomplete denylist, allowing arbitrary command execution through crafted base64-encoded pickle payloads.CVE-2026-159692026-07-30See advisory
CriticalSGLang uses an expert-parallel backup subsystem that exposes a ZeroMQ PULL socket on a routable network interface that does not contain authentication or deserialization safeguards, allowing an attacker to provide a malicious pickle file…CVE-2026-148902026-07-16See advisory
LowSGLang is Vulnerable to DoS via the data_hash FunctionCVE-2026-10775 · GHSA-jrcc-j37m-v8fg2026-06-04See advisory
LowSGLang: Reachable Assertion via lora_path in LoRAManager enables remote Denial of DerviceCVE-2026-10300 · GHSA-m2jr-x4gq-5rmj2026-06-02See advisory
CriticalSGLang: Unauthenticated RCE via --enable-custom-logit-processorCVE-2026-7304 · GHSA-36m8-w8qf-g76p2026-05-18See advisory
CriticalSGLanG: Multimodal scheduler deserializes untrusted pickle data on 0.0.0.0 ROUTER socketCVE-2026-7301 · GHSA-gwv6-pq6m-p3rq2026-05-18See advisory
CriticalSGLang's multimodal generation runtime has an unauthenticated path traversal vulnerabilityCVE-2026-7302 · GHSA-qwrp-wghp-94q22026-05-18See advisory
MediumSGLang has an Improper Input Validation/Injection IssueCVE-2026-7669 · GHSA-6m5f-673f-5vh72026-05-03See advisory
CriticalSGLang's reranking endpoint (/v1/rerank) achieves Remote Code Execution (RCE) when a model file containing a malcious tokenizer.chat_template is loaded, as the Jinja2 chat templates are rendered using an unsandboxed jinja2.Environment().CVE-2026-57602026-04-200.5.11
HighSGLangs `replay_request_dump.py` contains an insecure pickle.load() without validation and proper deserializationCVE-2026-3989 · GHSA-hvwj-8w5g-28rg2026-03-120.5.10
CriticalSGLang's encoder parallel disaggregation system is vulnerable to unauthenticated remote code execution through the disaggregation moduleCVE-2026-3060 · GHSA-jx93-g359-86wm2026-03-120.5.10
CriticalSGLang's multimodal generation module is vulnerable to unauthenticated remote code execution through the ZMQ brokerCVE-2026-3059 · GHSA-rgq9-fqf5-fv582026-03-120.5.10
MediumSGLang Remote Code Execution Vulnerability via Unsafe Deserialization in update_weights_from_tensorCVE-2025-10164 · GHSA-9w53-xr52-mwgj2025-09-090.5.4

CVEs matched by the NVD's product names, checked 2026-11-18. Where the vendor runs the service, its fix reaches you without an update.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].

This product uses the NVD API but is not endorsed or certified by the NVD. Product facts from github.com, checked 2026-11-18. Logos are their owners' marks, shown only to identify the products.