SglangApplication · Lmsys

CVE-2026-5760

CRITICAL · 9.8 CVSS v3.1 Published 2026-04-20
Fix available
A fix is available. Upgrade to 0.5.11 or later.
See remediation →
100/100
Remediation priority · Urgent
Public exploit Remotely reachable No privileges Zero-click Patch available

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

NVD · unedited
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().

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis · high confidence

SGLang's /v1/rerank endpoint executes arbitrary code through a malicious tokenizer.chat_template. The vulnerability stems from rendering Jinja2 chat templates using an unsandboxed jinja2.Environment(), which allows template injection to achieve Remote Code Execution without any security constraints.

MitigationImplement Jinja2 sandboxing by using jinja2.sandbox.SandboxedEnvironment() for template rendering, or disable chat_template processing entirely until proper sandboxing is verified.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.

NVD · CPE data
SglangApplication
Affected:< 0.5.11

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.

dbcve checks

Work through these to decide whether this CVE applies to you.

  1. Identify installed SGLang version
    Run `pip show sglang` or check the package version in your environment
    Affected if The installed version is lower than 0.5.11
  2. Verify if the /v1/rerank endpoint is exposed
    Check your SGLang server configuration and running endpoints; attempt a GET request to /v1/rerank to confirm accessibility
    Affected if The /v1/rerank endpoint is accessible without authentication
  3. Inspect tokenizer configuration for custom chat_template
    Examine the tokenizer configuration file or code that initializes the tokenizer; look for any chat_template parameter that could be user-controlled
    Affected if A custom or user-supplied chat_template is configured for the tokenizer
  4. Check jinja2 environment implementation for sandboxing
    Review the SGLang source code where jinja2.Environment() is instantiated for chat template rendering; verify whether jinja2.sandbox.SandboxedEnvironment() is used instead
    Affected if The code uses unsandboxed jinja2.Environment() for rendering chat_template

You are affected if you run SGLang version < 0.5.11 with the /v1/rerank endpoint exposed and either a custom chat_template is used or the jinja2 environment is unsandboxed.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

dbcve · scoped
Upgrade available Upgrade to 0.5.11 or later
Fixed in 0.5.11
Vendor patch github.com →
Interim mitigation

Implement Jinja2 sandboxing by using jinja2.sandbox.SandboxedEnvironment() for template rendering, or disable chat_template processing entirely until proper sandboxing is verified.

Recommended fix High confidence

0.5.11

  1. Upgrade SGLang to version 0.5.11 or later using your package manager (e.g., pip install sglang==0.5.11 or pip install --upgrade sglang)
  2. Verify the upgrade was successful by checking the installed version with: pip show sglang
  3. Ensure that any model files loaded through the /v1/rerank endpoint are from trusted sources, as a precaution

Generated from the published advisory — verify against the referenced sources before acting.

Fix this in Sglang Scoped from the published advisory
  • Consultation3.0 h
  • Implementation6.0 h
  • Testing3.0 h
  • Review / QA2.0 h
14.0 hours of engineering $2,490
Get the upgrade done

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $3,984.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-5760 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2026-5760 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data