Lucene search
+L

4 matches found

osv_cve
osv_cve
•added 2026/09/26 1:23 p.m.•50 views

CVE-2026-100651 vllm before 0.29.0 Denial of Service via Decoder Prompt Length Bypass

vLLM before 0.29.0 fails to enforce decoder prompt-length validation on the disaggregated serving endpoint /inference/v1/generate. When the request contains a 'features' multimodal payload, vllm/entrypoints/serve/disagg/serving.py builds a multimodal EngineInput directly from the caller-supplied...

7.1CVSS5.9AI score0.00384EPSS
SaveExploits1References4
EUVD
EUVD
•added 2026/09/26 1:23 p.m.•15 views

EUVD-2026-87745

vLLM before 0.29.0 fails to enforce decoder prompt-length validation on the disaggregated serving endpoint /inference/v1/generate. When the request contains a 'features' multimodal payload, vllm/entrypoints/serve/disagg/serving.py builds a multimodal EngineInput directly from the caller-supplied...

7.1CVSS5.9AI score0.00384EPSS
SaveExploits1References2
osv_debian
osv_debian
•added 2026/09/11 8:20 p.m.•19 views

DEBIAN-CVE-2026-89734

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: uvc: Fix null pointer dereference in uvcgvideoinit In uvcgvideoinit, if kthreadrunworker fails, the error logged uses uvcgerr, however, the pointer it uses: video-uvc is not assigned at this point, triggering a null...

6AI score0.00206EPSS
SaveExploits0References1
NVD
NVD
•added 2025/05/30 7:15 p.m.•35 views

CVE-2025-48944

vLLM is an inference and serving engine for large language models LLMs. In version 0.8.0 up to but excluding 0.9.0, the vLLM backend used with the /v1/chat/completions OpenAPI endpoint fails to validate unexpected or malformed input in the "pattern" and "type" fields when the tools functionality ...

6.5CVSS0.00642EPSS
SaveExploits1References2
Rows per page
Query Builder