225 matches found
CVE-2026-7669
A vulnerability was detected in sgl-project SGLang up to 0.5.9. Impacted is the function gettokenizer of the file python/sglang/srt/utils/hftransformersutils.py of the component HuggingFace Transformer Handler. The manipulation of the argument trustremotecode with the input False as part of Boole...
CVE-2026-7669 sgl-project SGLang HuggingFace Transformer hf_transformers_utils.py get_tokenizer code injection
A vulnerability was detected in sgl-project SGLang up to 0.5.9. Impacted is the function gettokenizer of the file python/sglang/srt/utils/hftransformersutils.py of the component HuggingFace Transformer Handler. The manipulation of the argument trustremotecode with the input False as part of Boole...
CVE-2026-7669
A vulnerability was detected in sgl-project SGLang up to 0.5.9. Impacted is the function gettokenizer of the file python/sglang/srt/utils/hftransformersutils.py of the component HuggingFace Transformer Handler. The manipulation of the argument trustremotecode with the input False as part of Boole...
EUVD-2026-26802
A vulnerability was detected in sgl-project SGLang up to 0.5.9. Impacted is the function gettokenizer of the file python/sglang/srt/utils/hftransformersutils.py of the component HuggingFace Transformer Handler. The manipulation results in deserialization. The attack can be executed remotely. A hi...
CVE-2026-7669 sgl-project SGLang HuggingFace Transformer hf_transformers_utils.py get_tokenizer code injection
A vulnerability was detected in sgl-project SGLang up to 0.5.9. Impacted is the function gettokenizer of the file python/sglang/srt/utils/hftransformersutils.py of the component HuggingFace Transformer Handler. The manipulation of the argument trustremotecode with the input False as part of Boole...
CVE-2026-7669
Affected software: sgl-project SGLang (up to 0.5.9). The vulnerability targets the function get_tokenizer in python/sglang/srt/utils/hf_transformers_utils.py within the HuggingFace Transformer Handler. Root cause is deserialization triggered by input manipulation. Impact is remote execution with ...
CVE-2026-7669: Improper Control of Generation of Code
A vulnerability was detected in sgl-project SGLang up to 0.5.9. Impacted is the function gettokenizer of the file python/sglang/srt/utils/hftransformersutils.py of the component HuggingFace Transformer Handler. The manipulation of the argument trustremotecode with the input False as part of Boole...
sglang 注入漏洞
SGLang is a programming language and runtime system developed by SGL-project, aimed at accelerating large model inference. Versions of SGLang 0.5.9 and earlier contained a injection vulnerability. This vulnerability stemmed from the operation of the gettokenizer function in the...
PT-2026-36639
Name of the Vulnerable Software and Affected Versions sgl-project SGLang versions prior to 0.6.0 Description A code injection issue exists in the HuggingFace Transformer Handler within the get tokenizer function of the python/sglang/srt/utils/hf transformers utils.py file. When a caller sets the...
CVE-2026-5760
SGLang's reranking endpoint /v1/rerank achieves Remote Code Execution RCE when a model file containing a malcious tokenizer.chattemplate is loaded, as the Jinja2 chat templates are rendered using an unsandboxed jinja2.Environment...
The vulnerability of the jinja2.Environment() function in the serving_rerank.py file of the high-performance LLM service framework SGLang allows a attacker to execute arbitrary code.
The vulnerability of the jinja2.Environment function in the servingrerank.py file of the high-performance LLM service framework SGLang is related to incorrect code generation practices. Exploiting this vulnerability allows an attacker to execute arbitrary code remotely...
SGLang CVE-2026-5760 (CVSS 9.8) Enables RCE via Malicious GGUF Model Files
A critical security vulnerability has been disclosed in SGLang that, if successfully exploited, could result in remote code execution on susceptible systems. The vulnerability, tracked as CVE-2026-5760 , carries a CVSS score of 9.8 out of 10.0. It has been described as a case of command injection...
Arbitrary Code Injection
Overview sglang is a SGLang is a fast serving framework for large language models and vision language models. Affected versions of this package are vulnerable to Arbitrary Code Injection via the reranking endpoint when a model file containing a malicious tokenizer.chattemplate is loaded, due to...
CVE-2026-5760
SGLang's reranking endpoint /v1/rerank achieves Remote Code Execution RCE when a model file containing a malcious tokenizer.chattemplate is loaded, as the Jinja2 chat templates are rendered using an unsandboxed jinja2.Environment...
CVE-2026-5760 CVE-2026-5760
SGLang's reranking endpoint /v1/rerank achieves Remote Code Execution RCE when a model file containing a malcious tokenizer.chattemplate is loaded, as the Jinja2 chat templates are rendered using an unsandboxed jinja2.Environment...
CVE-2026-5760
SGLang's reranking endpoint /v1/rerank achieves Remote Code Execution RCE when a model file containing a malcious tokenizer.chattemplate is loaded, as the Jinja2 chat templates are rendered using an unsandboxed jinja2.Environment...
CVE-2026-5760
The SGLang high-performance LLM service framework is vulnerable to Remote Code Execution (RCE) via its reranking endpoint (/v1/rerank). The root cause is the use of an unsandboxed jinja2.Environment() within the _get_jinja_env() function in serving_rerank.py. An attacker can achieve RCE by loadin...
CVE-2026-5760: Improper Control of Generation of Code
SGLang's reranking endpoint /v1/rerank achieves Remote Code Execution RCE when a model file containing a malcious tokenizer.chattemplate is loaded, as the Jinja2 chat templates are rendered using an unsandboxed jinja2.Environment...
sglang 安全漏洞
SGLang is a programming language and runtime system developed by SGL-project, aimed at accelerating large model inference. SGLang has a security vulnerability. This vulnerability arises from loading model files that contain malicious tokenizer/chattemplate components. As a result, the Jinja2 chat...
SGLang is vulnerable to remote code execution when rendering chat templates from a model file
Overview A remote code execution vulnerability has been discovered in the SGLang project, specifically in the reranking endpoint /v1/rerank. A CVE has been assigned to track the vulnerability; CVE-2026-5760. An attacker can create a malicious model for SGLang to achieve RCE. Successful exploitati...