{"cve":"CVE-2025-47277","nvd":{"published":"2025-05-20T18:15:46.730","modified":"2026-06-17T09:27:39.253","status":"Analyzed","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.","cvss_v4":null,"cvss_v3":{"version":"3.1","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","score":9.8},"cwes":["CWE-502"],"references":["https://docs.vllm.ai/en/latest/deployment/security.html","https://github.com/vllm-project/vllm/commit/0d6e187e88874c39cda7409cf673f9e6546893e7","https://github.com/vllm-project/vllm/pull/15988","https://github.com/vllm-project/vllm/security/advisories/GHSA-hjq4-87xh-g4fv"],"products":["vllm:vllm"],"source":"nvd","synced_at":"2026-10-19T22:01:57.636215869+00:00"},"epss":{"cve":"CVE-2025-47277","score":0.00964,"percentile":0.61687,"date":"2026-10-31"},"kev":null,"osv":[{"id":"GHSA-hjq4-87xh-g4fv","url":"https://osv.dev/vulnerability/GHSA-hjq4-87xh-g4fv","summary":"vLLM Allows Remote Code Execution via PyNcclPipe Communication Service","modified":"2026-08-07T08:12:11.894773937Z","packages":[{"ecosystem":"PyPI","name":"vllm","purl":"pkg:pypi/vllm","ranges":[">=0.6.5 <0.8.5"],"fixed":["0.8.5"]}]},{"id":"PYSEC-2026-567","url":"https://osv.dev/vulnerability/PYSEC-2026-567","summary":"vLLM Allows Remote Code Execution via PyNcclPipe Communication Service","modified":"2026-07-01T20:23:11.300418Z","packages":[{"ecosystem":"PyPI","name":"vllm","purl":"pkg:pypi/vllm","ranges":[">=0.6.5 <0.8.5"],"fixed":["0.8.5"]}]}],"attribution":["This product uses the NVD API but is not endorsed or certified by the NVD.","EPSS scores: FIRST Exploit Prediction Scoring System, https://www.first.org/epss","Known exploited vulnerabilities: CISA Known Exploited Vulnerabilities Catalog, https://www.cisa.gov/known-exploited-vulnerabilities-catalog","Package advisories: OSV (https://osv.dev), from the GitHub Advisory Database, PyPA, Go, RustSec and other ecosystem databases, under CC-BY 4.0 or CC0","CVE records: the CVE Program's CVE List (https://www.cve.org), under its terms of use (https://www.cve.org/Legal/TermsOfUse). CVE is a registered trademark of The MITRE Corporation; this product is not affiliated with the CVE Program."]}