Skip to main content

SGLang CVE-2026-15976

| EUVDEUVD-2026-51264 CRITICAL
Deserialization of Untrusted Data (CWE-502)
2026-07-30 certcc GHSA-r344-357p-w9pp
9.8
CVSS 3.1 · Vendor: certcc
Share

Severity by source

Vendor (certcc) PRIMARY
9.8 CRITICAL
AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
vuln.today AI
9.8 CRITICAL

Network-reachable management endpoint is unauthenticated by default (PR:N) and the pickle fallback yields deterministic RCE (AC:L), giving full C/I/A impact on the host.

3.1 AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
4.0 AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Primary rating from Vendor (certcc).

CVSS VectorVendor: certcc

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

Lifecycle Timeline

4
Analysis Generated
Jul 31, 2026 - 20:22 vuln.today
CVSS changed
Jul 31, 2026 - 20:22 NVD
9.8 (CRITICAL)
CVE Published
Jul 30, 2026 - 18:07 cve.org
UNKNOWN (no severity yet)
CVE Published
Jul 30, 2026 - 18:07 cve.org
CRITICAL 9.8

DescriptionCVE.org

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.

AnalysisAI

Remote code execution in SGLang (versions up to and including 0.5.15) allows attackers to run arbitrary code on the inference server by abusing the /update_weights_from_disk endpoint, which falls back to torch.load(..., weights_only=False) and thus deserializes attacker-controlled pickle streams embedded in .bin model-weight files. Because SGLang's HTTP serving API is typically exposed without authentication, an attacker able to reach the endpoint and influence the loaded weights path can achieve code execution as the serving process. …

Unlock full vulnerability intelligence

  • Risk assessment & exploitation conditions
  • Attack chain visualization
  • Remediation with exact patch versions
  • Threat intelligence from 22 sources
  • Personal watchlist & email alerts

Free forever · No credit card required

Attack ChainAIDerived

Hypothetical attack flow derived from CVE metadata

Access
Reach exposed SGLang management API
Delivery
POST to /update_weights_from_disk with malicious .bin path
Exploit
torch.load weights_only=False deserializes pickle
Execution
Gadget executes arbitrary code
Impact
RCE as serving process user

Vulnerability AssessmentAI

Exploitation Exploitation requires reaching SGLang's /update_weights_from_disk endpoint and causing it to load an attacker-influenced legacy PyTorch .bin file, which triggers the torch.load(..., weights_only=False) pickle-deserialization fallback. … Additional conditions and limiting factors are described in the full assessment.
Risk Assessment The signals are mixed and worth weighing carefully. … Full risk analysis with EPSS, KEV, and SSVC signal comparison available after sign-in.
Exploit Scenario An attacker who can reach an SGLang server's management API sends a request to /update_weights_from_disk pointing at a malicious .bin checkpoint (for example a booby-trapped HuggingFace repo or a path the attacker controls). When SGLang loads it via torch.load with weights_only=False, the embedded pickle gadget executes, giving the attacker code execution as the serving user. …
Remediation Upgrade SGLang to a release newer than 0.5.15 that addresses GHSA-wf98-gv64-5wrf (consult the advisory at https://github.com/sgl-project/sglang/security/advisories/GHSA-wf98-gv64-5wrf for the exact fixed version; a released patched version is not independently confirmed from the provided data, so verify the fixed tag in the advisory before deploying). … Detailed patch versions, workarounds, and compensating controls in full report.

Recommended ActionAI

Within 24 hours, identify all production and development SGLang deployments and document their current versions, network exposure, and data sensitivity. …

Sign in for detailed remediation steps and compensating controls.

Threat intelligence, references, and detailed analysis are available after sign-in.

More in Sglang

View all
CVE-2026-15969 CRITICAL
9.8 Jul 30

Remote code execution in SGLang (versions up to and including 0.5.15) allows unauthenticated attackers to run arbitrary

CVE-2026-3059 CRITICAL
9.8 Mar 12

SGLang's multimodal generation module deserializes untrusted data with pickle.loads() over an unauthenticated ZMQ broker

CVE-2026-3060 CRITICAL
9.8 Mar 12

SGLang's encoder parallel disaggregation system is vulnerable to unauthenticated RCE through pickle deserialization in t

CVE-2026-7304 CRITICAL
9.8 May 18

Unauthenticated remote code execution in SGLang (the LLM/multimodal generation serving runtime) affecting version 5.10 a

CVE-2026-5760 CRITICAL
9.8 Apr 20

Remote code execution in SGLang 0.5.9's /v1/rerank endpoint allows unauthenticated attackers to execute arbitrary code b

CVE-2026-15971 CRITICAL
9.8 Jul 30

Remote code execution in SGLang (versions ≤ v0.5.15) allows attackers to achieve arbitrary code execution through the op

CVE-2026-7301 CRITICAL
9.8 May 18

Unauthenticated remote code execution affects SGLang, an LLM/multimodal inference-serving framework, at version 5.10, wh

CVE-2026-14890 CRITICAL
9.1 Jul 16

Unauthenticated remote code execution in SGLang (versions 0 through 0.5.14) arises when the expert-parallel backup subsy

CVE-2026-7302 CRITICAL
9.1 May 18

Arbitrary file write in SGLang's multimodal generation runtime (version 5.10) allows a remote, unauthenticated attacker

CVE-2026-3989 HIGH
7.8 Mar 12

High severity vulnerability in SGLang. SGLangs `replay_request_dump.py` contains an insecure pickle.load() without valid

CVE-2026-15978 HIGH
7.5 Jul 30

SGLang versions up to and including v0.5.15 expose unauthenticated network endpoints that allow complete model weight ex

CVE-2026-15977 HIGH
7.5 Jul 30

Unauthenticated credential leakage in SGLang's /server_info HTTP endpoint exposes configured API keys and SSL keyfile pa

Share

CVE-2026-15976 vulnerability details – vuln.today

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy