Lucene search
+L

5 matches found

Github Security Blog
Github Security Blog
•added 2025/12/02 5:34 p.m.•63 views

vLLM vulnerable to remote code execution via transformers_utils/get_config

Summary vllm has a critical remote code execution vector in a config class named NemotronNanoVLConfig. When vllm loads a model config that contains an automap entry, the config class resolves that mapping with getclassfromdynamicmodule... and immediately instantiates the returned class. This...

8.8CVSS7.2AI score0.00708EPSS
SaveExploits0References8Affected Software1
osv_ghsa
osv_ghsa
•added 2025/12/02 5:34 p.m.•20 views

GHSA-8FR4-5Q9J-M8GM vLLM vulnerable to remote code execution via transformers_utils/get_config

Summary vllm has a critical remote code execution vector in a config class named NemotronNanoVLConfig. When vllm loads a model config that contains an automap entry, the config class resolves that mapping with getclassfromdynamicmodule... and immediately instantiates the returned class. This...

7.1CVSS7.2AI score0.00708EPSS
SaveExploits0References8
NVD
NVD
•added 2025/12/01 11:15 p.m.•23 views

CVE-2025-66448

vLLM is an inference and serving engine for large language models LLMs. Prior to 0.11.1, vllm has a critical remote code execution vector in a config class named NemotronNanoVLConfig. When vllm loads a model config that contains an automap entry, the config class resolves that mapping with...

8.8CVSS0.00708EPSS
SaveExploits0References3
Snyk
Snyk
•added 2025/12/01 11:04 p.m.•25 views

Arbitrary Code Injection

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Arbitrary Code Injection via the config class named NemotronNanoVLConfig. An attacker can execute arbitrary code on the host system by publishing a...

8.8CVSS7.4AI score0.00708EPSS
SaveExploits0References2
Positive Technologies
Positive Technologies
•added 2025/12/01 12:00 a.m.•30 views

PT-2025-48580

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.11.1 Description vLLM is an inference and serving engine for large language models LLMs. A critical issue exists in the Nemotron Nano VL Config class where remote code execution can occur. When vLLM loads a model...

8.8CVSS6.8AI score0.00708EPSS
SaveExploits0References20
Rows per page
Query Builder