SglangApplication · Lmsys

CVE-2026-15976

CRITICAL · 9.8 CVSS v3.1 Published 2026-07-30
Fix available
A fix is available. Upgrade to after 0.5.15 or later.
See remediation →
100/100
Remediation priority · Urgent
Remotely reachable No privileges Zero-click 3 weeks old

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 contains a RCE vulnerability when attempting to load model weights from a HuggingFace repository, specifically within the /update_weights_from_disk, where torch.load(..., weights_only=False) fallback enables pickle deserialization of .bin files.

In the news

Third-party coverage
Trending covered by 1 outlet this week · latest 6d ago

Surfaced from public web coverage — external links open in a new tab.

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 contains a critical RCE vulnerability in the /update_weights_from_disk endpoint which uses torch.load() with weights_only=False, allowing arbitrary pickle deserialization of .bin model weight files. An attacker who can control or supply a malicious .bin file can achieve remote code execution.

MitigationRestrict network access to the /update_weights_from_disk endpoint and validate/sanitize all model weight files before loading. Consider implementing a secure loading mechanism or switching to weights_only=True if compatible with legitimate use cases.

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:<= 0.5.15

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. Check installed SGLang version
    Run `pip show sglang` or `pip list | grep sglang` to identify the installed version number
    Affected if The installed version is 0.5.15 or lower (any version <= 0.5.15)
  2. Verify /update_weights_from_disk endpoint exists
    Inspect SGLang server source code for the route handler definition at the /update_weights_from_disk path, or check API documentation for available endpoints
    Affected if The endpoint is present in the codebase (vulnerable code path exists)
  3. Confirm torch.load is called with weights_only=False
    Search the SGLang source code for torch.load() calls within the weight update handler and inspect whether the weights_only parameter is set to False or omitted
    Affected if torch.load() is invoked without weights_only=True in the weight loading logic
  4. Check network exposure of the weight update API
    Review server startup configuration and network bindings to determine if the API endpoint is accessible over network (not localhost-only)
    Affected if The endpoint is exposed to untrusted network sources

You are affected if running SGLang version 0.5.15 or lower AND the /update_weights_from_disk endpoint exists with torch.load() called without weights_only=True.

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 a release after 0.5.15
Interim mitigation

Restrict network access to the /update_weights_from_disk endpoint and validate/sanitize all model weight files before loading. Consider implementing a secure loading mechanism or switching to weights_only=True if compatible with legitimate use cases.

Recommended fix Moderate confidence

Latest stable SGLang release (check GitHub security advisories for the specific version number containing the fix)

  1. Check the official SGLang GitHub repository (github.com/sgl-project/sglang) for security advisories and releases addressing this vulnerability
  2. Identify the current SGLang version in use (typically via `pip show sglang` or checking environment)
  3. Upgrade to the latest stable SGLang release that includes the security fix: run `pip install --upgrade sglang`
  4. Alternatively, if a specific fixed version is mentioned in security advisories, install that version explicitly: `pip install sglang==<fixed_version>`
  5. After upgrading, verify the fix is applied by checking that `torch.load()` calls in the codebase no longer use `weights_only=False` when loading untrusted model weights
  6. As a mitigation before patching, avoid loading model weights from untrusted or unverified HuggingFace repositories
  7. If you must load external weights, ensure they are from trusted sources and have been verified
Caveat Standard upgrade considerations apply - review release notes for any breaking changes between your current version and the fixed version

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

Fix this in Sglang Scoped from the published advisory
  • Consultation4.0 h
  • Implementation8.0 h
  • Testing6.0 h
  • Review / QA4.0 h
22.0 hours of engineering $3,860
Get the upgrade done

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $6,176.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-15976 — 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-2026-15976 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