Lucene search
+L

747 matches found

CNNVD
CNNVD
added 2025/04/30 12:00 a.m.13 views

vLLM 安全漏洞

vLLM is a high throughput and memory efficient inference and service engine for LLM from the vLLM open source. A security vulnerability exists in vLLM versions prior to 0.8.0 through 0.8.5, which stems from inefficiencies in the input preprocessing logic that could lead to resource exhaustion...

7.5CVSS6.3AI score0.00502EPSS
SaveExploits1References2
Github Security Blog
Github Security Blog
added 2025/04/29 2:52 p.m.31 views

vLLM Vulnerable to Remote Code Execution via Mooncake Integration

Impacted Deployments Note that vLLM instances that do NOT make use of the mooncake integration are NOT vulnerable. Description vLLM integration with mooncake is vaulnerable to remote code execution due to using pickle based serialization over unsecured ZeroMQ sockets. The vulnerable sockets were...

10CVSS7.7AI score0.01667EPSS
SaveExploits1References7Affected Software1
Github Security Blog
Github Security Blog
added 2025/04/29 2:50 p.m.37 views

Data exposure via ZeroMQ on multi-node vLLM deployment

Impact In a multi-node vLLM deployment, vLLM uses ZeroMQ for some multi-node communication purposes. The primary vLLM host opens an XPUB ZeroMQ socket and binds it to ALL interfaces. While the socket is always opened for a multi-node deployment, it is only used when doing tensor parallelism acros...

7.5CVSS7.6AI score0.00574EPSS
SaveExploits1References9Affected Software1
Positive Technologies
Positive Technologies
added 2025/04/29 12:00 a.m.11 views

PT-2025-18215

Name of the Vulnerable Software and Affected Versions vLLM versions 0.5.2 through 0.8.5 Description The issue affects vLLM, a high-throughput and memory-efficient inference and serving engine for LLMs. In a multi-node vLLM deployment, vLLM uses ZeroMQ for some multi-node communication purposes,...

7.5CVSS7.1AI score0.00574EPSS
SaveExploits1References23
Veracode
Veracode
added 2025/04/23 1:57 p.m.12 views

Denial Of Service (DoS)

vllm is vulnerable to Denial of Service DoS. The vulnerability is due to unbounded in-memory cache growth due to allowing unique schema requests to continually populate the grammar cache, potentially exhausting system RAM...

7AI score
SaveExploits0
OSV
OSV
added 2025/04/23 2:26 a.m.33 views

GHSA-GGPF-24JW-3FCW CVE-2025-24357 Malicious model remote code execution fix bypass with PyTorch < 2.6.0

Description https://github.com/vllm-project/vllm/security/advisories/GHSA-rh4j-5rhw-hr54 reported a vulnerability where loading a malicious model could result in code execution on the vllm host. The fix applied to specify weightsonly=True to calls to torch.load did not solve the problem prior to...

9.8CVSS7AI score
SaveExploits0References4
Github Security Blog
Github Security Blog
added 2025/04/15 9:21 p.m.203 views

vLLM vulnerable to Denial of Service by abusing xgrammar cache

Impact This report is to highlight a vulnerability in XGrammar, a library used by the structured output feature in vLLM. The XGrammar advisory is here: https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3 The xgrammar library is the default backend used by vLLM to support...

6.8AI score
SaveExploits0References5Affected Software1
OSV
OSV
added 2025/04/15 9:21 p.m.9 views

GHSA-HF3C-WXG2-49Q9 vLLM vulnerable to Denial of Service by abusing xgrammar cache

Impact This report is to highlight a vulnerability in XGrammar, a library used by the structured output feature in vLLM. The XGrammar advisory is here: https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3 The xgrammar library is the default backend used by vLLM to support...

6.5CVSS5.9AI score
SaveExploits0References5
Chainguard
Chainguard
added 2025/04/15 7:13 a.m.44 views

CVE-2025-1979 vulnerabilities

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

6.4CVSS7.5AI score0.00192EPSS
SaveExploits0
Chainguard
Chainguard
added 2025/04/15 7:13 a.m.10 views

GHSA-W4RH-FGX7-Q63M vulnerabilities

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

7.5AI score
SaveExploits0
Chainguard
Chainguard
added 2025/04/14 7:23 p.m.14 views

GHSA-389X-67PX-MJG3 vulnerabilities

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

5.2AI score
SaveExploits0
Chainguard
Chainguard
added 2025/04/14 7:23 p.m.29 views

CVE-2025-32381 vulnerabilities

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

6.5CVSS6.3AI score0.00498EPSS
SaveExploits0
Positive Technologies
Positive Technologies
added 2025/04/03 12:00 a.m.8 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 score0.00959EPSS
SaveExploits1References20
Chainguard
Chainguard
added 2025/03/25 4:12 a.m.45 views

CVE-2024-9052 vulnerabilities

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

6.9AI score
SaveExploits0
Chainguard
Chainguard
added 2025/03/25 4:12 a.m.20 views

GHSA-PGR7-MHP5-FGJP vulnerabilities

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

5.2AI score
SaveExploits0
Veracode
Veracode
added 2025/03/24 3:58 a.m.26 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 score0.00728EPSS
SaveExploits0References6Affected Software1
RedhatCVE
RedhatCVE
added 2025/03/22 11:53 a.m.15 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 score0.01356EPSS
SaveExploits1References5
RedhatCVE
RedhatCVE
added 2025/03/22 11:47 a.m.11 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
SaveExploits0References5
Chainguard
Chainguard
added 2025/03/22 10:12 a.m.31 views

CVE-2025-29783 vulnerabilities

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

9CVSS8.3AI score0.00728EPSS
SaveExploits0
Chainguard
Chainguard
added 2025/03/22 10:12 a.m.11 views

GHSA-X3M8-F7G5-QHM7 vulnerabilities

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

5.3AI score
SaveExploits0
Rows per page
Query Builder