Lucene search
+L

5 matches found

PyPA
PyPA
•added 2026/07/07 4:03 p.m.•27 views

vLLM affected by RCE via auto_map dynamic module loading during model initialization

SummaryvLLM loads Hugging Face automap dynamic modules during model resolution without gating on trustremotecode, allowing attacker-controlled Python code in a model repo/path to execute at server startup.--- ImpactAn attacker who can influence the model repo/path local directory or remote Huggin...

9.8CVSS7.2AI score0.0083EPSS
SaveExploits1References8Affected Software1
OSV
OSV
•added 2026/01/21 9:13 p.m.•15 views

CVE-2026-22807 vLLM affected by RCE via auto_map dynamic module loading during model initialization

vLLM is an inference and serving engine for large language models LLMs. Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face automap dynamic modules during model resolution without gating on trustremotecode, allowing attacker-controlled Python code in a model repo/path ...

8.8CVSS6.6AI score
SaveExploits0References19
attackerkb
attackerkb
•added 2026/01/21 9:13 p.m.•23 views

CVE-2026-22807

vLLM is an inference and serving engine for large language models LLMs. Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face automap dynamic modules during model resolution without gating on trustremotecode, allowing attacker-controlled Python code in a model repo/path ...

9.8CVSS6.5AI score0.0083EPSS
SaveExploits1References5Affected Software1
Cvelist
Cvelist
•added 2026/01/21 9:13 p.m.•38 views

CVE-2026-22807 vLLM affected by RCE via auto_map dynamic module loading during model initialization

vLLM is an inference and serving engine for large language models LLMs. Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face automap dynamic modules during model resolution without gating on trustremotecode, allowing attacker-controlled Python code in a model repo/path ...

8.8CVSS0.0083EPSS
SaveExploits1References4
EUVD
EUVD
•added 2026/01/21 9:13 p.m.•17 views

EUVD-2026-3678

vLLM is an inference and serving engine for large language models LLMs. Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face automap dynamic modules during model resolution without gating on trustremotecode, allowing attacker-controlled Python code in a model repo/path ...

8.8CVSS6.5AI score0.0083EPSS
SaveExploits1References5
Rows per page
Query Builder