CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service
Attackers can execute arbitrary code via unsafe deserialization in PyNcclPipe if exposed to untrusted networks.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2025-47277?
CVE-2025-47277 is a critical unsafe deserialization vulnerability in Vllm Vllm, published on 20 May 2025. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official 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.
Weakness: CWE-502
Which versions are affected by CVE-2025-47277?
3 open source packages ship an affected version, including vllm. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
vllm PyPI | From 0.6.5 | 0.8.5 |
vllm PyPI | From 0.6.5 | 0.8.5 |
vllm PyPI | From 0.6.5 | 0.8.5 |
Products include Vllm Vllm.
How do I fix CVE-2025-47277?
Upgrade vllm to 0.8.5 or later.
Upgrade, and only deserialise data from trusted sources or with an allow-list of types. More about Unsafe deserialization.
Is CVE-2025-47277 being exploited?
There is no known exploitation of CVE-2025-47277 in the wild and no public exploit code.
Other vulnerabilities in Vllm Vllm
- CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration
- CVE-2026-22778 vLLM leaks a heap address when PIL throws an error
- CVE-2024-11041 Remote Code Execution in vllm-project/vllm
- CVE-2026-48746 vLLM: OpenAI auth bypass
- CVE-2025-29783 vLLM Allows Remote Code Execution via Mooncake Integration
Sources
Also known as GHSA-hjq4-87xh-g4fv, PYSEC-2026-567.