Lucene search
+L

640 matches found

Chainguard
Chainguard
added 2025/04/15 7:13 a.m.34 views

CVE-2025-1979 vulnerabilities

Vulnerabilities for packages: py3.10-vllm-cuda-12.6...

6.4CVSS7.5AI score0.00183EPSS
Exploits0
Chainguard
Chainguard
added 2025/04/15 7:13 a.m.8 views

GHSA-W4RH-FGX7-Q63M vulnerabilities

Vulnerabilities for packages: py3.10-vllm-cuda-12.6...

7.5AI score
Exploits0
Chainguard
Chainguard
added 2025/04/14 7:23 p.m.12 views

GHSA-389X-67PX-MJG3 vulnerabilities

Vulnerabilities for packages: py3.10-vllm-cuda-11.8...

5.2AI score
Exploits0
Chainguard
Chainguard
added 2025/04/14 7:23 p.m.23 views

CVE-2025-32381 vulnerabilities

Vulnerabilities for packages: py3.10-vllm-cuda-11.8...

6.5CVSS6.3AI score0.00466EPSS
Exploits0
Positive Technologies
Positive Technologies
added 2025/04/03 12:0 a.m.6 views

PT-2025-22278

Name of the Vulnerable Software and Affected Versions vLLM versions 0.6.5 through 0.8.4 Description vLLM, an inference and serving engine for large language models LLMs, contains a remote code execution issue. This impacts environments utilizing the PyNcclPipe KV cache transfer integration with t...

10CVSS7.8AI score0.00943EPSS
Exploits1References20
Chainguard
Chainguard
added 2025/03/25 4:12 a.m.38 views

CVE-2024-9052 vulnerabilities

Vulnerabilities for packages: py3.10-vllm-cuda-11.8...

6.9AI score
Exploits0
Chainguard
Chainguard
added 2025/03/25 4:12 a.m.17 views

GHSA-PGR7-MHP5-FGJP vulnerabilities

Vulnerabilities for packages: py3.10-vllm-cuda-11.8...

5.2AI score
Exploits0
Veracode
Veracode
added 2025/03/24 3:58 a.m.23 views

Remote Code Execution (RCE)

vllm is vulnerable to Remote Code Execution RCE. The vulnerability is due to unsafe deserialization exposed over ZMQ/TCP on all network interfaces when vLLM is configured to use Mooncake, allowing an attacker to execute arbitrary code on distributed hosts...

9CVSS8.6AI score0.0082EPSS
Exploits0References6Affected Software1
RedhatCVE
RedhatCVE
added 2025/03/22 11:53 a.m.11 views

CVE-2024-9053

A flaw was found in the vLLM AsyncEngineRPCServer. This vulnerability allows remote code execution via deserialization of untrusted data. Mitigation Mitigation for this issue is either not available or the currently available options don't meet the Red Hat Product Security criteria comprising eas...

2.6CVSS9.7AI score0.01274EPSS
Exploits1References5
RedhatCVE
RedhatCVE
added 2025/03/22 11:47 a.m.8 views

CVE-2024-9052

A flaw was found in the vLLM distributed training API. This vulnerability allows remote code execution via unsafe deserialization, which uses pickle.loads without sanitization...

2.6CVSS9.7AI score
Exploits0References5
Chainguard
Chainguard
added 2025/03/22 10:12 a.m.27 views

CVE-2025-29783 vulnerabilities

Vulnerabilities for packages: py3.10-vllm-cuda-11.8, tritonserver-backend-vllm...

9CVSS8.3AI score0.0082EPSS
Exploits0
Chainguard
Chainguard
added 2025/03/22 10:12 a.m.10 views

GHSA-X3M8-F7G5-QHM7 vulnerabilities

Vulnerabilities for packages: py3.10-vllm-cuda-11.8, tritonserver-backend-vllm...

5.3AI score
Exploits0
OSV
OSV
added 2025/03/20 12:32 p.m.3 views

GHSA-PGR7-MHP5-FGJP vLLM deserialization vulnerability in vllm.distributed.GroupCoordinator.recv_object

vllm-project vllm version 0.6.0 contains a vulnerability in the distributed training API. The function vllm.distributed.GroupCoordinator.recvobject deserializes received object bytes using pickle.loads without sanitization, leading to a remote code execution vulnerability. Maintainer perspective...

9.8CVSS6.5AI score
Exploits0References6
OSV
OSV
added 2025/03/20 12:32 p.m.63 views

GHSA-CJ47-QJ6G-X7R4 vLLM allows Remote Code Execution by Pickle Deserialization via AsyncEngineRPCServer() RPC server entrypoints

vllm-project vllm version 0.6.0 contains a vulnerability in the AsyncEngineRPCServer RPC server entrypoints. The core functionality runserverloop calls the function makehandlercoro, which directly uses cloudpickle.loads on received messages without any sanitization. This can result in remote code...

9.8CVSS8.1AI score0.01274EPSS
Exploits1References4
Github Security Blog
Github Security Blog
added 2025/03/20 12:32 p.m.15 views

vLLM allows Remote Code Execution by Pickle Deserialization via AsyncEngineRPCServer() RPC server entrypoints

vllm-project vllm version 0.6.0 contains a vulnerability in the AsyncEngineRPCServer RPC server entrypoints. The core functionality runserverloop calls the function makehandlercoro, which directly uses cloudpickle.loads on received messages without any sanitization. This can result in remote code...

9.8CVSS7.8AI score0.01274EPSS
Exploits1References4Affected Software1
Github Security Blog
Github Security Blog
added 2025/03/20 12:32 p.m.29 views

vLLM deserialization vulnerability in vllm.distributed.GroupCoordinator.recv_object

vllm-project vllm version 0.6.0 contains a vulnerability in the distributed training API. The function vllm.distributed.GroupCoordinator.recvobject deserializes received object bytes using pickle.loads without sanitization, leading to a remote code execution vulnerability. Maintainer perspective...

6.9AI score
Exploits0References6Affected Software1
vulnersOsv
vulnersOsv
added 2025/03/20 12:32 p.m.5 views

aana (>=0.2.1 <=0.2.2.2), acai-swarm (=0.1.0) +218 more potentially affected by CVE-2024-11041 via vllm (>=0.10.0 <=0.9.2)

vllm PYPI version =0.10.0, =0.2.1, =1.2.1, =0.0.0, =2.3.5, =0.0.7, =0.0.1b1, =0.1.15, =0.2.4, =1.0.0, =1.0.14 and more Source cves: CVE-2024-11041 Source advisory: SNYK:PYTHON-VLLM-9513025...

9.8CVSS6.7AI score0.01424EPSS
Exploits1
OSV
OSV
added 2025/03/20 12:32 p.m.8 views

GHSA-5VQR-WPRC-CPP7 vLLM Deserialization of Untrusted Data vulnerability

vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue API function. The function uses pickle.loads to parse received sockets directly, leading to a remote code execution vulnerability. An attacker can exploit this by sending a malicious payload to the MessageQueue,...

9.8CVSS7.6AI score0.01424EPSS
Exploits1References4
Github Security Blog
Github Security Blog
added 2025/03/20 12:32 p.m.27 views

vLLM Deserialization of Untrusted Data vulnerability

vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue API function. The function uses pickle.loads to parse received sockets directly, leading to a remote code execution vulnerability. An attacker can exploit this by sending a malicious payload to the MessageQueue,...

9.8CVSS8.2AI score0.01424EPSS
Exploits1References4Affected Software1
NVD
NVD
added 2025/03/20 10:15 a.m.32 views

CVE-2024-9053

vllm-project vllm version 0.6.0 contains a vulnerability in the AsyncEngineRPCServer RPC server entrypoints. The core functionality runserverloop calls the function makehandlercoro, which directly uses cloudpickle.loads on received messages without any sanitization. This can result in remote code...

9.8CVSS0.01274EPSS
Exploits1References1
Rows per page
Query Builder