CVE-2026-7669

Sažetak

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 of the argument trust_remote_code with the input False as part of Boolean results in code injection. The attack can be executed remotely. A high complexity level is associated with this attack. The exploitability is considered difficult. In get_tokenizer(), when the caller passes trust_remote_code=False and HuggingFace transformers v5 returns a TokenizersBackend instance (the generic fallback for tokenizer classes not in the registry), SGLang silently re-invokes AutoTokenizer.from_pretrained with trust_remote_code=True, overriding the caller's explicit security setting. A model repository containing a malicious tokenizer.py referenced via auto_map in tokenizer_config.json will execute arbitrary Python in the SGLang process during this second call. No log line or warning is emitted. The override affects all current SGLang versions because transformers==5.3.0 is pinned in pyproject.toml. Both tokenizer_mode="auto" and tokenizer_mode="slow" are affected. The exploit is now public and may be used. The vendor was contacted early about this disclosure but did not respond in any way.

Reference

CVSS

Base:	5.1
Impact:	6.4
Exploitability:	4.9

Pristup

Vektor	Složenost	Autentikacija
NETWORK	HIGH	NONE

Impact

Povjerljivost	Cjelovitost	Dostupnost
PARTIAL	PARTIAL	PARTIAL

CVSS vektor

AV:N/AC:H/Au:N/C:P/I:P/A:P

Zadnje važnije ažuriranje

05-05-2026 - 19:15

Objavljeno

02-05-2026 - 22:16