Lucene search
+L

720 matches found

OSV
OSV
added 2025/11/21 1:18 a.m.5 views

CVE-2025-62164 VLLM deserialization vulnerability leading to DoS and potential RCE

vLLM is an inference and serving engine for large language models LLMs. From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability could lead to a crash denial-of-service and potentially remote code execution RCE, exists in the Completions API endpoint. When processing user-supplied...

8.8CVSS8.1AI score
SaveExploits0References5
CVE
CVE
added 2025/11/21 1:18 a.m.67 views

CVE-2025-62164

The CVE affects vLLM (inference/serving engine) before 0.11.1, where the Completions API loads user-supplied prompt embeddings with torch.load() lacking proper validation. A PyTorch 2.8.0 change disables sparse-tensor invariants checks, allowing crafted tensors to bypass bounds checks and trigger...

8.8CVSS7.8AI score0.00892EPSS
SaveExploits0References3Affected Software1
CNNVD
CNNVD
added 2025/11/21 12:00 a.m.9 views

vLLM 缓冲区错误漏洞

vLLM is a vLLM open source high throughput and memory efficient inference and service engine for LLM. A buffer error vulnerability exists in vLLM versions 0.10.2 through prior to 0.11.1, which stems from the presence of a memory corruption in the Completions API endpoint that could lead to a cras...

8.8CVSS7.9AI score0.00892EPSS
SaveExploits0References3
Github Security Blog
Github Security Blog
added 2025/11/20 9:26 p.m.23 views

vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`

Summary The /v1/chat/completions and /tokenize endpoints allow a chattemplatekwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chattemplatekwargs parameters, it is possible to block processing of the API server for long...

6.5CVSS6.8AI score0.00365EPSS
SaveExploits0References10Affected Software1
OSV
OSV
added 2025/11/20 9:26 p.m.8 views

GHSA-69J4-GRXJ-J64P vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`

Summary The /v1/chat/completions and /tokenize endpoints allow a chattemplatekwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chattemplatekwargs parameters, it is possible to block processing of the API server for long...

6.5CVSS6.1AI score0.00365EPSS
SaveExploits0References10
Snyk
Snyk
added 2025/11/20 9:26 p.m.21 views

Allocation of Resources Without Limits or Throttling

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling via the applyhfchattemplate method. An authenticated user can cause the server to become...

7.1CVSS6.9AI score0.00365EPSS
SaveExploits0References2
Snyk
Snyk
added 2025/11/20 8:59 p.m.13 views

Out-of-bounds Write

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Out-of-bounds Write via the todense function in the Completions API endpoint when processing user-supplied prompt embeddings. An attacker can achiev...

8.8CVSS8.2AI score0.00892EPSS
SaveExploits0References4
Github Security Blog
Github Security Blog
added 2025/11/20 8:59 p.m.19 views

vLLM deserialization vulnerability leading to DoS and potential RCE

Summary A memory corruption vulnerability that leading to a crash denial-of-service and potentially remote code execution RCE exists in vLLM versions 0.10.2 and later, in the Completions API endpoint. When processing user-supplied prompt embeddings, the endpoint loads serialized tensors using...

8.8CVSS8.3AI score0.00892EPSS
SaveExploits0References8Affected Software1
OSV
OSV
added 2025/11/20 8:59 p.m.18 views

GHSA-MRW7-HF4F-83PF vLLM deserialization vulnerability leading to DoS and potential RCE

Summary A memory corruption vulnerability that leading to a crash denial-of-service and potentially remote code execution RCE exists in vLLM versions 0.10.2 and later, in the Completions API endpoint. When processing user-supplied prompt embeddings, the endpoint loads serialized tensors using...

8.8CVSS6.5AI score0.00892EPSS
SaveExploits0References8
Chainguard
Chainguard
added 2025/10/11 1:24 a.m.20 views

CVE-2025-61620 vulnerabilities

Vulnerabilities for packages: py3-vllm-cuda-12.4, tritonserver-backend-vllm-cuda-12.9...

5.7AI score0.00207EPSS
SaveExploits1
Chainguard
Chainguard
added 2025/10/11 1:24 a.m.25 views

CVE-2025-59425 vulnerabilities

Vulnerabilities for packages: py3-vllm-cuda-12.4, tritonserver-backend-vllm-cuda-12.9...

7.5CVSS6AI score0.00528EPSS
SaveExploits1
Chainguard
Chainguard
added 2025/10/11 1:24 a.m.35 views

CVE-2025-6242 vulnerabilities

Vulnerabilities for packages: py3-vllm-cuda-12.4, tritonserver-backend-vllm-cuda-12.9...

7.1CVSS6AI score0.00229EPSS
SaveExploits0
Chainguard
Chainguard
added 2025/10/11 1:24 a.m.7 views

GHSA-6FVQ-23CW-5628 vulnerabilities

Vulnerabilities for packages: py3-vllm-cuda-12.4, tritonserver-backend-vllm-cuda-12.9...

5.2AI score
SaveExploits0
Chainguard
Chainguard
added 2025/10/11 1:24 a.m.11 views

GHSA-WR9H-G72X-MWHM vulnerabilities

Vulnerabilities for packages: py3-vllm-cuda-12.4, tritonserver-backend-vllm-cuda-12.9...

5.2AI score
SaveExploits0
Chainguard
Chainguard
added 2025/10/11 1:24 a.m.23 views

GHSA-3F6C-7FW2-PPM4 vulnerabilities

Vulnerabilities for packages: py3-vllm-cuda-12.4, tritonserver-backend-vllm-cuda-12.9...

5.2AI score
SaveExploits0
Snyk
Snyk
added 2025/10/07 10:14 p.m.11 views

Server-side Request Forgery (SSRF)

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Server-side Request Forgery SSRF via the loadfromurl and loadfromurlasync methods of the MediaConnector class, which fetch and process media from...

8.3CVSS7.1AI score0.00229EPSS
SaveExploits0References3
OSV
OSV
added 2025/10/07 10:14 p.m.12 views

GHSA-3F6C-7FW2-PPM4 vLLM is vulnerable to Server-Side Request Forgery (SSRF) through `MediaConnector` class

Summary A Server-Side Request Forgery SSRF vulnerability exists in the MediaConnector class within the vLLM project's multimodal feature set. The loadfromurl and loadfromurlasync methods fetch and process media from user-provided URLs without adequate restrictions on the target hosts. This allows...

7.1CVSS6.5AI score0.00229EPSS
SaveExploits0References6
OSV
OSV
added 2025/10/07 9:35 p.m.13 views

GHSA-6FVQ-23CW-5628 vLLM: Resource-Exhaustion (DoS) through Malicious Jinja Template in OpenAI-Compatible Server

Summary A resource-exhaustion denial-of-service vulnerability exists in multiple endpoints of the OpenAI-Compatible Server due to the ability to specify Jinja templates via the chattemplate and chattemplatekwargs parameters. If an attacker can supply these parameters to the API, they can cause a...

6.5CVSS6.9AI score0.00207EPSS
SaveExploits1References4
Snyk
Snyk
added 2025/10/07 9:35 p.m.13 views

Allocation of Resources Without Limits or Throttling

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling through the chattemplate and chattemplatekwargs parameters. An attacker can cause excessive CPU...

7.1CVSS6.9AI score0.00207EPSS
SaveExploits1References2
NVD
NVD
added 2025/10/07 8:15 p.m.13 views

CVE-2025-6242

A Server-Side Request Forgery SSRF vulnerability exists in the MediaConnector class within the vLLM project's multimodal feature set. The loadfromurl and loadfromurlasync methods fetch and process media from user-provided URLs without adequate restrictions on the target hosts. This allows an...

7.1CVSS0.00229EPSS
SaveExploits0References2
Rows per page
Query Builder