Browse / Unsafe Model Loading and Supply Chain / CVE-2026-7669
SGLang has an Improper Input Validation/Injection Issue
- Class
- Unsafe Model Loading and Supply Chain (filed by a model that read the advisory)
- Technique
- Unsafe deserialisation
- Affected
- sglang (PyPI)
- CVSS
- CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L
- EPSS
- 0.4% chance of exploitation in 30 days
How it works, in short
A remotely supplied model or tokenizer reference causes unsafe deserialisation inside the transformers helper that loads the tokenizer. (Our summary, written by a model. The source text is below.)
Details
A vulnerability was detected in sgl-project SGLang up to 0.5.9. Impacted is the function get_tokenizer of the file python/sglang/srt/utils/hf_transformers_utils.py of the component HuggingFace Transformer Handler. The manipulation results in deserialization. The attack can be executed remotely. A high complexity level is associated with this attack. The exploitability is considered difficult. The vendor was contacted early about this disclosure but did not respond in any way.
References
- https://nvd.nist.gov/vuln/detail/CVE-2026-7669
- https://github.com/gouldnicholas/CVE-2026-7669-PoC
- https://github.com/sgl-project/sglang
- https://vuldb.com/submit/799263
- https://vuldb.com/vuln/360817
- https://vuldb.com/vuln/360817/cti
Source: GitHub Advisory Database, used under CC BY 4.0.