Vulnerabilities

Vulnerability · CVE-2026-7669

A vulnerability was detected in sgl-project SGLang up to 0.5.9.

Published May 2, 2026 · catalog updated Jun 17, 2026 · A vulnerability was detected

Check if you run it

No confirmed exploitation is on record for CVE-2026-7669. EPSS is 0.42%. Act only if a listed version of A vulnerability was detected is installed.

Severity

Medium6.3

Known exploitation

Not in CISA/VulnCheck KEV

EPSS

0.42%

Remediation

Not established

Affected products

See sources for product scope

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.

No affected version ranges are stored yet. Use the vendor advisory before you decide this record does not apply.