Lucene search
+L

6 matches found

osv_pysec
osv_pysec
•added 2026/10/26 5:17 p.m.•20 views

PYSEC-2026-4345

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonicid values in public multimodal features.kwargsdata. In scale-out deployments with shared-memory multimodal caching enabled, workers trust...

8.8CVSS7.7AI score0.0051EPSS
SaveExploits0References4
Vulnrichment
Vulnrichment
•added 2026/10/26 4:54 p.m.•5 views

CVE-2026-115912 vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonicid values in public multimodal features.kwargsdata. In scale-out deployments with shared-memory multimodal caching enabled, workers trust...

7.5CVSS7.7AI score0.0051EPSS
SaveExploits0References4
osv_cve
osv_cve
•added 2026/10/26 4:54 p.m.•39 views

CVE-2026-115912 vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonicid values in public multimodal features.kwargsdata. In scale-out deployments with shared-memory multimodal caching enabled, workers trust...

7.5CVSS7.7AI score0.0051EPSS
SaveExploits0References6
Mend
Mend
•added 2026/10/26 4:54 p.m.•23 views

CVE-2026-115912

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonicid values in public multimodal features.kwargsdata. In scale-out deployments with shared-memory multimodal caching enabled, workers trust...

7.7CVSS7.7AI score0.0051EPSS
SaveExploits0References6
CVE
CVE
•added 2026/10/26 4:54 p.m.•91 views

CVE-2026-115912

In versions prior to 0.32.0 , the vLLM inference and serving engine for large language models is vulnerable to arbitrary Python execution. An authenticated caller can exploit this by placing forged shared-memory address and monotonic_id values in public multimodal features.kwargs_data. In scale-o...

8.8CVSS7.7AI score0.0051EPSS
SaveExploits0References4Affected Software1
Cvelist
Cvelist
•added 2026/10/26 4:54 p.m.•32 views

CVE-2026-115912 vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonicid values in public multimodal features.kwargsdata. In scale-out deployments with shared-memory multimodal caching enabled, workers trust...

7.5CVSS0.0051EPSS
SaveExploits0References4
Rows per page
Query Builder