Skip to main content

Over 150 LLM Providers · Over 5,300 Models The most extensible AI-powered pentesting platform. Open source. Star on GitHub

CVE-2026-15974

6.5 · MEDIUM
Published Jul 30, 2026 lmsys CWE-918

Overview

CVE-2026-15974 is a medium-severity vulnerability affecting lmsys sglang. It was published on July 30, 2026 and has a CVSS 3.1 base score of 6.5 (MEDIUM).

This vulnerability has a CVSS 3.1 base score of 6.5, rated MEDIUM. It can be exploited remotely over the network. Some level of privileges is required for exploitation.

Technical Description

SGLang 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.

Remediation

Check the references section for vendor advisories and patches from lmsys. Update sglang to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.

Affected Products

Vendor Product Versions Status
lmsys sglang 0 Affected

Frequently Asked Questions

What is CVE-2026-15974?

CVE-2026-15974 is a medium-severity vulnerability affecting lmsys sglang. It was published on July 30, 2026 and has a CVSS 3.1 base score of 6.5 (MEDIUM).

How severe is CVE-2026-15974?

This vulnerability has a CVSS 3.1 base score of 6.5, rated MEDIUM. It can be exploited remotely over the network. Some level of privileges is required for exploitation.

How do I fix or remediate CVE-2026-15974?

Check the references section for vendor advisories and patches from lmsys. Update sglang to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.

How can CyberStrike help with CVE-2026-15974?

CyberStrike's AI-powered security agents can automatically detect CVE-2026-15974 across your infrastructure using autonomous pentesting, DAST scanning, and HackBrowser. The platform continuously monitors for known vulnerabilities and provides actionable remediation guidance prioritized by real-world exploitability.

Browse by year 2026