CVE-2026-7669

sgl-project SGLang HuggingFace Transformer hf_transformers_utils.py get_tokenizer code injection

Published May 2, 2026 CVSS 4.0 · 6.3 Medium EPSS < 1% KEV · Not listed
Description
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.

Remediation

No solution or workaround provided in the CVE record

Tracking

Sign in to view the affected projects.

Advisories

Source ID Title
Github GHSA Github GHSA GHSA-6m5f-673f-5vh7 SGLang has an Improper Input Validation/Injection Issue
History
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'poc', 'Technical Impact': 'partial'}, 'version': '2.0.3'}

Type Values Removed Values Added
First Time appeared Sgl-project
Sgl-project sglang
Vendors & Products Sgl-project
Sgl-project sglang
Type Values Removed Values Added
Weaknesses CWE-20
CWE-502
Type Values Removed Values Added
Description 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. 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.
Title sgl-project SGLang HuggingFace Transformer hf_transformers_utils.py get_tokenizer deserialization sgl-project SGLang HuggingFace Transformer hf_transformers_utils.py get_tokenizer code injection
Weaknesses CWE-74
CWE-94
References
Metrics cvssV2_0

{'score': 5.1, 'vector': 'AV:N/AC:H/Au:N/C:P/I:P/A:P/E:ND/RL:ND/RC:UR'}

cvssV3_0

{'score': 5.6, 'vector': 'CVSS:3.0/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L/E:X/RL:X/RC:R'}

cvssV3_1

{'score': 5.6, 'vector': 'CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L/E:X/RL:X/RC:R'}

cvssV2_0

{'score': 5.1, 'vector': 'AV:N/AC:H/Au:N/C:P/I:P/A:P/E:POC/RL:ND/RC:UR'}

cvssV3_0

{'score': 5.6, 'vector': 'CVSS:3.0/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R'}

cvssV3_1

{'score': 5.6, 'vector': 'CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R'}

Type Values Removed Values Added
Description 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.
Title sgl-project SGLang HuggingFace Transformer hf_transformers_utils.py get_tokenizer deserialization
Weaknesses CWE-20
CWE-502
References
Metrics cvssV2_0

{'score': 5.1, 'vector': 'AV:N/AC:H/Au:N/C:P/I:P/A:P/E:ND/RL:ND/RC:UR'}

cvssV3_0

{'score': 5.6, 'vector': 'CVSS:3.0/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L/E:X/RL:X/RC:R'}

cvssV3_1

{'score': 5.6, 'vector': 'CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L/E:X/RL:X/RC:R'}

cvssV4_0

{'score': 6.3, 'vector': 'CVSS:4.0/AV:N/AC:H/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:X'}

Weaknesses

Sources

Status
PUBLISHED
Assigner
VulDB
Published
Updated
May 5, 2026, 12:31 AM
Reserved
May 2, 2026, 8:00 AM
Status
Deferred
Published
May 2, 2026, 10:16 PM
Modified
Oct 26, 2026, 8:10 PM