Lucene search
+L

758 matches found

Chainguard
Chainguard
added 2026/09/04 8:26 p.m.15 views

GHSA-83VM-P52W-F9PW vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9...

5.3AI score
SaveExploits0
Chainguard
Chainguard
added 2026/09/04 8:26 p.m.11 views

CVE-2026-44223 vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9...

6.5CVSS5.1AI score0.00367EPSS
SaveExploits0
RedhatCVE
RedhatCVE
added 2026/09/01 10:32 a.m.8 views

CVE-2026-37237

A flaw was found in vLLM. Remote attackers can exploit this vulnerability by providing a URL to an excessively large media file. The AsyncMediaIO.fetchaudio and AsyncMediaIO.fetchimage functions, responsible for fetching user-supplied media, do not limit the response size. This oversight allows a...

7.5CVSS5.8AI score0.00532EPSS
SaveExploits0References6
NVD
NVD
added 2026/08/28 4:17 p.m.11 views

CVE-2026-37237

vLLM up to and including 0.17.0 allows remote attackers to cause a Denial of Service via memory exhaustion. The AsyncMediaIO.fetchaudio and AsyncMediaIO.fetchimage functions in multimodal/inputs.py fetch user-supplied media URLs using aiohttp and call r.read without enforcing a maximum response...

7.5CVSS0.00532EPSS
SaveExploits0References3
Cvelist
Cvelist
added 2026/08/28 12:00 a.m.35 views

CVE-2026-37237

vLLM up to and including 0.17.0 allows remote attackers to cause a Denial of Service via memory exhaustion. The AsyncMediaIO.fetchaudio and AsyncMediaIO.fetchimage functions in multimodal/inputs.py fetch user-supplied media URLs using aiohttp and call r.read without enforcing a maximum response...

0.00532EPSS
SaveExploits0References3
CVE
CVE
added 2026/08/28 12:00 a.m.19 views

CVE-2026-37237

vLLM (versions up to and including 0.17.0 ) is vulnerable to a Denial of Service via memory exhaustion . The AsyncMediaIO.fetch_audio and AsyncMediaIO.fetch_image functions in multimodal/inputs.py fetch user-supplied media URLs using aiohttp and call r.read() without enforcing a maximum response ...

7.5CVSS5.8AI score0.00532EPSS
SaveExploits0References3
EUVD
EUVD
added 2026/08/28 12:00 a.m.8 views

EUVD-2026-67775

vLLM up to and including 0.17.0 allows remote attackers to cause a Denial of Service via memory exhaustion. The AsyncMediaIO.fetchaudio and AsyncMediaIO.fetchimage functions in multimodal/inputs.py fetch user-supplied media URLs using aiohttp and call r.read without enforcing a maximum response...

7.5CVSS5.8AI score0.00532EPSS
SaveExploits0References3
RedhatCVE
RedhatCVE
added 2026/08/27 1:37 p.m.7 views

CVE-2026-78684

A flaw was found in vLLM. Unauthenticated attackers can exploit this vulnerability by activating the DeepStream backend during a request. This allows them to initialize the process-wide GPU decode pool and submit video that bypasses resource controls, leading to a partial denial of service for...

6.9CVSS5.3AI score0.00327EPSS
SaveExploits0References6
RedhatCVE
RedhatCVE
added 2026/08/27 11:52 a.m.9 views

CVE-2026-73560

A flaw was found in vLLM, an inference and serving engine for large language models. The MiMoV2OmniMultiModalProcessor component improperly handles attacker-controlled image and audio strings, bypassing security protections. This vulnerability allows a remote attacker to perform Server-Side Reque...

6.5CVSS5.6AI score0.00319EPSS
SaveExploits0References7
RedhatCVE
RedhatCVE
added 2026/08/27 11:52 a.m.9 views

CVE-2026-71486

A flaw was found in vLLM. An authenticated API client can exploit derender endpoints by providing oversized GenerateResponse objects. These endpoints process the objects without enforcing output bounds or response-size limits. This can lead to excessive consumption of CPU and memory resources,...

4.3CVSS5.4AI score0.00341EPSS
SaveExploits0References7
Chainguard
Chainguard
added 2026/08/27 2:18 a.m.16 views

GHSA-87X5-VMC3-756J vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9, tritonserver-backend-vllm-cuda-13.0...

5.3AI score
SaveExploits0
Chainguard
Chainguard
added 2026/08/27 2:18 a.m.16 views

CVE-2026-73559 vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9, tritonserver-backend-vllm-cuda-13.0...

6.5CVSS5.1AI score0.00472EPSS
SaveExploits0
NVD
NVD
added 2026/08/25 12:16 p.m.9 views

CVE-2026-78684

vLLM before 0.27.0 fails to properly classify DeepStream as a GPU backend and omits pixel-limit enforcement in its decode path. Unauthenticated attackers can activate DeepStream at request time to initialize the process-wide GPU decode pool and submit video that bypasses resource controls, causin...

6.9CVSS0.00327EPSS
SaveExploits0References3
EUVD
EUVD
added 2026/08/25 11:33 a.m.8 views

EUVD-2026-65457

vLLM before 0.27.0 fails to properly classify DeepStream as a GPU backend and omits pixel-limit enforcement in its decode path. Unauthenticated attackers can activate DeepStream at request time to initialize the process-wide GPU decode pool and submit video that bypasses resource controls, causin...

6.9CVSS5.4AI score0.00327EPSS
SaveExploits0References3
Cvelist
Cvelist
added 2026/08/25 11:33 a.m.27 views

CVE-2026-78684 vLLM before 0.27.0 Denial of Service via DeepStream Backend

vLLM before 0.27.0 fails to properly classify DeepStream as a GPU backend and omits pixel-limit enforcement in its decode path. Unauthenticated attackers can activate DeepStream at request time to initialize the process-wide GPU decode pool and submit video that bypasses resource controls, causin...

6.9CVSS0.00327EPSS
SaveExploits0References3
OSV
OSV
added 2026/08/25 11:33 a.m.6 views

CVE-2026-78684 vLLM before 0.27.0 Denial of Service via DeepStream Backend

vLLM before 0.27.0 fails to properly classify DeepStream as a GPU backend and omits pixel-limit enforcement in its decode path. Unauthenticated attackers can activate DeepStream at request time to initialize the process-wide GPU decode pool and submit video that bypasses resource controls, causin...

6.9CVSS5.5AI score
SaveExploits0References5
Vulnrichment
Vulnrichment
added 2026/08/25 11:33 a.m.6 views

CVE-2026-78684 vLLM before 0.27.0 Denial of Service via DeepStream Backend

vLLM before 0.27.0 fails to properly classify DeepStream as a GPU backend and omits pixel-limit enforcement in its decode path. Unauthenticated attackers can activate DeepStream at request time to initialize the process-wide GPU decode pool and submit video that bypasses resource controls, causin...

6.9CVSS5.3AI score0.00327EPSS
SaveExploits0References3
CVE
CVE
added 2026/08/25 11:33 a.m.22 views

CVE-2026-78684

vLLM versions prior to 0.27.0 are susceptible to a denial-of-service condition through improper handling of the DeepStream backend. The root cause is a failure to classify DeepStream as a GPU backend combined with missing pixel-limit enforcement in the decode path. An unauthenticated attacker can...

6.9CVSS5.4AI score0.00327EPSS
SaveExploits0References3
Chainguard
Chainguard
added 2026/08/24 8:25 p.m.23 views

CVE-2026-54234 vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9, tritonserver-backend-vllm-cuda-13.0...

7.5CVSS5.8AI score0.00616EPSS
SaveExploits1
Chainguard
Chainguard
added 2026/08/24 8:25 p.m.26 views

CVE-2026-47155 vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9, tritonserver-backend-vllm-cuda-13.0...

6.5CVSS5.8AI score0.00249EPSS
SaveExploits0
Rows per page
Query Builder