Vulnerabilities · 2025 · Vllm
CVE-2025-47277
Vllm vulnerability
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.
High priority: this vulnerability is rated critical and can be attacked over the network without a login.
Affected products
Vllm. The exact versions are in the references.
What to do now
- Check your exposureFind out whether Vllm runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Limit access until thenIf you cannot update at once, take the system off the internet or restrict who can reach it.
References
- github.com/vllm-project/vllm/security/advisories/GHSA-hjq4-87xh-g4fv · Exploit
- github.com/vllm-project/vllm/commit/0d6e187e88874c39cda7409cf673f9e6546893e7 · Patch
- github.com/vllm-project/vllm/pull/15988 · Patch
- docs.vllm.ai/en/latest/deployment/security.html
- nvd.nist.gov/vuln/detail/CVE-2025-47277
- github.com/advisories/GHSA-hjq4-87xh-g4fv
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-567.yaml
- github.com/vllm-project/vllm
- nvd.nist.gov/vuln/detail/CVE-2025-47277
- cve.org/CVERecord?id=CVE-2025-47277
More vulnerabilities in Vllm products
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.