CVE-2025-47277
NVIDIA vLLM Unauthenticated Remote Code Execution
Description
vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments using the `PyNcclPipe` KV cache transfer integration with the V0 engine. No other configurations are affected. vLLM supports the use of the `PyNcclPipe` class to establish a peer-to-peer communication domain for data transmission between distributed nodes. The GPU-side KV-Cache transmission is implemented through the `PyNcclCommunicator` class, while CPU-side control message passing is handled via the `send_obj` and `recv_obj` methods on the CPU side. The intention was that this interface should only be exposed to a private network using the IP address specified by the `--kv-ip` CLI parameter. The vLLM documentation covers how this must be limited to a secured network. The default and intentional behavior from PyTorch is that the `TCPStore` interface listens on ALL interfaces, regardless of what IP address is provided. The IP address given was only used as a client-side address to use. vLLM was fixed to use a workaround to force the `TCPStore` instance to bind its socket to a specified private interface. As of version 0.8.5, vLLM limits the `TCPStore` socket to the private interface as configured.
INFO
Published Date :
May 20, 2025, 6:15 p.m.
Last Modified :
Aug. 13, 2025, 4:35 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | CRITICAL | [email protected] |
Public PoC/Exploit Available at Github
CVE-2025-47277 has a 1 public
PoC/Exploit available at Github.
Go to the Public Exploits tab to see the list.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2025-47277.
| URL | Resource |
|---|---|
| https://docs.vllm.ai/en/latest/deployment/security.html | Technical Description |
| https://github.com/vllm-project/vllm/commit/0d6e187e88874c39cda7409cf673f9e6546893e7 | Patch |
| https://github.com/vllm-project/vllm/pull/15988 | Issue Tracking Patch |
| https://github.com/vllm-project/vllm/security/advisories/GHSA-hjq4-87xh-g4fv | Exploit Vendor Advisory |
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2025-47277 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2025-47277
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
一个 CVE 漏洞预警知识库，无 exp/poc，部分包含修复方案。A knowledge base of CVE security vulnerability, no PoCs/exploits.
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2025-47277 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2025-47277 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
Initial Analysis by [email protected]
Aug. 13, 2025
Action Type Old Value New Value Added CPE Configuration OR *cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* versions from (including) 0.6.5 up to (excluding) 0.8.5 Added Reference Type GitHub, Inc.: https://docs.vllm.ai/en/latest/deployment/security.html Types: Technical Description Added Reference Type GitHub, Inc.: https://github.com/vllm-project/vllm/commit/0d6e187e88874c39cda7409cf673f9e6546893e7 Types: Patch Added Reference Type GitHub, Inc.: https://github.com/vllm-project/vllm/pull/15988 Types: Issue Tracking, Patch Added Reference Type GitHub, Inc.: https://github.com/vllm-project/vllm/security/advisories/GHSA-hjq4-87xh-g4fv Types: Exploit, Vendor Advisory -
New CVE Received by [email protected]
May. 20, 2025
Action Type Old Value New Value Added Description vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments using the `PyNcclPipe` KV cache transfer integration with the V0 engine. No other configurations are affected. vLLM supports the use of the `PyNcclPipe` class to establish a peer-to-peer communication domain for data transmission between distributed nodes. The GPU-side KV-Cache transmission is implemented through the `PyNcclCommunicator` class, while CPU-side control message passing is handled via the `send_obj` and `recv_obj` methods on the CPU side. The intention was that this interface should only be exposed to a private network using the IP address specified by the `--kv-ip` CLI parameter. The vLLM documentation covers how this must be limited to a secured network. The default and intentional behavior from PyTorch is that the `TCPStore` interface listens on ALL interfaces, regardless of what IP address is provided. The IP address given was only used as a client-side address to use. vLLM was fixed to use a workaround to force the `TCPStore` instance to bind its socket to a specified private interface. As of version 0.8.5, vLLM limits the `TCPStore` socket to the private interface as configured. Added CVSS V3.1 AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Added CWE CWE-502 Added Reference https://docs.vllm.ai/en/latest/deployment/security.html Added Reference https://github.com/vllm-project/vllm/commit/0d6e187e88874c39cda7409cf673f9e6546893e7 Added Reference https://github.com/vllm-project/vllm/pull/15988 Added Reference https://github.com/vllm-project/vllm/security/advisories/GHSA-hjq4-87xh-g4fv