MediumVulnerability

CVE-2026-7669: SGLang deserialization of untrusted data in get_tokenizer

Source: NVD(opens in a new tab)
Identifier: CVE-2026-7669
Published: May 2, 2026
Record updated: October 9, 2026

Affected: sglang <= 0.5.9
Fixed in: No fixed version was stated when the source was last read.
Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.4%

Summary

CVE-2026-7669 affects sgl-project SGLang up to 0.5.9, specifically the function get_tokenizer in python/sglang/srt/utils/hf_transformers_utils.py within the HuggingFace Transformer Handler component. The flaw is a deserialization of untrusted data (CWE-502) that can be exploited remotely, with high attack complexity and difficult exploitability. The vendor did not respond to early disclosure, and the CVSS 4.0 base score is 6.3 (MEDIUM) per VulDB, with NVD assessment not yet provided.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

CVSS score: 5.6(medium)
CVSS vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L
Attack vector: network
Attack complexity: high
Privileges required: none
User interaction: none
EPSS: 0.4%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 9, 2026.
Disclosure date: May 2, 2026

Weaknesses and techniques

Weakness (CWE): CWE-20
CWE-502
Attack pattern (CAPEC): CAPEC-586
AI threat technique (MITRE ATLAS): AML.T0010

Affected

Packages: sglang@<= 0.5.9

Classification

Attack type: Supply chain
Attack sophistication: Advanced
AI component targeted: Inference
Impact: Confidentiality,
Integrity,
Availability
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-7669

First tracked: May 3, 2026 at 02:07 AM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 90% (self-assessed)

Affected packages in the Exposure Registry

Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.

sglangPyPILLM dependency since 2024-01-16 · 2 tracked dependents

Summary

Mitigation

Affected packages in the Exposure Registry

Related items