Focus on lmsys vulnerabilities and metrics.
Last updated: 16 Jun 2026, 22:25 UTC
This page consolidates all known Common Vulnerabilities and Exposures (CVEs) associated with lmsys. We track both calendar-based metrics (using fixed periods) and rolling metrics (using gliding windows) to give you a comprehensive view of security trends and risk evolution. Use these insights to assess risk and plan your patching strategy.
For a broader perspective on cybersecurity threats, explore the comprehensive list of CVEs by vendor and product. Stay updated on critical vulnerabilities affecting major software and hardware providers.
Total lmsys CVEs: 7
Earliest CVE date: 12 Mar 2026, 12:15 UTC
Latest CVE date: 03 Jun 2026, 23:16 UTC
Latest CVE reference: CVE-2026-10775
30-day Count (Rolling): 4
365-day Count (Rolling): 7
Calendar-based Variation
Calendar-based Variation compares a fixed calendar period (e.g., this month versus the same month last year), while Rolling Growth Rate uses a continuous window (e.g., last 30 days versus the previous 30 days) to capture trends independent of calendar boundaries.
Month Variation (Calendar): 300.0%
Year Variation (Calendar): 0%
Month Growth Rate (30-day Rolling): 300.0%
Year Growth Rate (365-day Rolling): 0.0%
Average CVSS: 0.34
Max CVSS: 2.4
Critical CVEs (≥9): 0
| Range | Count |
|---|---|
| 0.0-3.9 | 7 |
| 4.0-6.9 | 0 |
| 7.0-8.9 | 0 |
| 9.0-10.0 | 0 |
These are the five CVEs with the highest CVSS scores for lmsys, sorted by severity first and recency.
A vulnerability was determined in sgl-project SGLang up to 0.5.11. Affected by this vulnerability is the function data_hash of the component Cache Handler. This manipulation causes denial of service. The attack is restricted to local execution. A high degree of complexity is needed for the attack. The exploitation appears to be difficult. The exploit has been publicly disclosed and may be utilized. The pull request to fix this issue awaits acceptance.
SGLangs multimodal generation runtime is vulnerable to unauthenticated remote code execution when the --enable-custom-logit-processor option is enabled, as Python objects loaded via dill.loads() will be deserialized without validation.
SGLangs multimodal generation runtime is vulnerable to an unauthenticated path traversal vulnerability, allowing an attacker to write arbitrary files anywhere the server process has write access, by including ../ sequences in the upload filename when sent to specific endpoints.
SGLangs multimodal generation runtime scheduler's ROUTER socket binds to 0.0.0.0 by default and contains a sink that calls pickle.loads() on incoming messages, enabling RCE when exposed to the internet.
SGLang'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().
SGLang' encoder parallel disaggregation system is vulnerable to unauthenticated remote code execution through the disaggregation module, which deserializes untrusted data using pickle.loads() without authentication.
SGLang's multimodal generation module is vulnerable to unauthenticated remote code execution through the ZMQ broker, which deserializes untrusted data using pickle.loads() without authentication.