CVE Vulnerabilities

CVE-2026-7669

Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')

Published: May 02, 2026 | Modified: May 05, 2026
CVSS 3.x
N/A
Source:
NVD
CVSS 2.x
RedHat/V2
RedHat/V3
Ubuntu
root.io logo minimus.io logo echo.ai logo

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 callers 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.

Weakness

The product constructs all or part of a command, data structure, or record using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify how it is parsed or interpreted when it is sent to a downstream component.

Potential Mitigations

References