🛡️ CVE-2026-15976 — sglang

🔴 CVSS 9.8 — Critical ✅ No Known Exploit CWE-502 NVD
9.8
CVSS Score
0 Low4 Medium7 High9 Critical10

Description

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.

How this vulnerability can be exploited

This issue can be reached over the network, attack complexity is low, an attacker needs no privileges on the target. No user interaction is required. The scope is unchanged, so the impact stays within the vulnerable component. Rated impact: confidentiality high, integrity high, availability high.

Weakness class

CVE-2026-15976 is classified as CWE-502: Deserialization of Untrusted Data. Serialised data from an untrusted source is reconstructed into objects, which can trigger code during the process.

Affected software

CVE-2026-15976 is recorded against 1 package.

  • sglang (fixed in 0.5.15)

Timeline and source

Published on 30 July 2026 and last revised on 4 August 2026. No public exploit is currently recorded for this entry. Record sourced from NVD.

References

github.com
thoughts.apoorvdayal.com
thoughts.apoorvdayal.com

Details

Severity CRITICAL
CVSS Score 9.8
CVSS Vector CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CWE CWE-502
Public Exploit ✅ No
Source NVD
Published 2026-07-30
Updated 2026-08-11
Modified 2026-08-04
Fix URL N/A

Affected Packages

Software From version Fixed in
sglang — 0.5.15

Similar Threats

Exploit Protection

Are you running sglang?

CVE-2026-15976 carries CVSS 9.8 Critical rating. BotEraser checks your installation against this and other known CVE records, and blocks IPs associated with exploit activity.

Check My Site For CVE-2026-15976 →

No credit card required  ·  Results in minutes

ⓘ Data Notice: The information presented above has been compiled from publicly available internet sources. Boteraser aggregates this data solely for informational purposes and does not independently classify, evaluate, or endorse any findings about the vulnerabilities listed. The accuracy and completeness of this information is the sole responsibility of the original publishers. Boteraser and its operators accept no liability for any decisions made based on this data.