https://vulnerability.circl.lu/sightings/feed 2026-07-13T15:37:30.383778+00:00 Vulnerability-Lookup info@circl.lu python-feedgen Contains only the most 10 recent sightings. https://vulnerability.circl.lu/sighting/a1688f64-8cd0-46fd-a4e8-9f10802cf970/export 2026-07-13T15:37:30.395307+00:00 Automation user https://vulnerability.circl.lu/user/automation {"uuid": "a1688f64-8cd0-46fd-a4e8-9f10802cf970", "vulnerability_lookup_origin": "1a89b78e-f703-45f3-bb86-59eb712668bd", "author": "9f56dd64-161d-43a6-b9c3-555944290a09", "vulnerability": "GHSA-hjq4-87xh-g4fv", "type": "seen", "source": "https://infosec.exchange/users/cR0w/statuses/114541634791270960", "content": "", "creation_timestamp": "2025-05-20T18:44:05.055749Z"} 2025-05-20T18:44:05.055749+00:00 https://vulnerability.circl.lu/sighting/9d2a416f-6898-4741-807a-f54b860329c0/export 2026-07-13T15:37:30.396502+00:00 Automation user https://vulnerability.circl.lu/user/automation {"uuid": "9d2a416f-6898-4741-807a-f54b860329c0", "vulnerability_lookup_origin": "1a89b78e-f703-45f3-bb86-59eb712668bd", "author": "9f56dd64-161d-43a6-b9c3-555944290a09", "vulnerability": "GHSA-HJQ4-87XH-G4FV", "type": "published-proof-of-concept", "source": "https://t.me/DarkWebInformer_CVEAlerts/17023", "content": "\ud83d\udd17 DarkWebInformer.com - Cyber Threat Intelligence\n\ud83d\udccc CVE ID: CVE-2025-47277\n\ud83d\udd25 CVSS Score: 9.8 (cvssV3_1, Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H)\n\ud83d\udd39 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\u00a0`PyNcclPipe`\u00a0class to establish a peer-to-peer communication domain for data transmission between distributed nodes. The GPU-side KV-Cache transmission is implemented through the\u00a0`PyNcclCommunicator`\u00a0class, while CPU-side control message passing is handled via the\u00a0`send_obj`\u00a0and\u00a0`recv_obj`\u00a0methods on the CPU side.\u200b 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.\n\ud83d\udccf Published: 2025-05-20T17:32:27.034Z\n\ud83d\udccf Modified: 2025-05-20T17:32:27.034Z\n\ud83d\udd17 References:\n1. https://github.com/vllm-project/vllm/security/advisories/GHSA-hjq4-87xh-g4fv\n2. https://github.com/vllm-project/vllm/pull/15988\n3. https://github.com/vllm-project/vllm/commit/0d6e187e88874c39cda7409cf673f9e6546893e7\n4. https://docs.vllm.ai/en/latest/deployment/security.html", "creation_timestamp": "2025-05-20T17:43:46.000000Z"} 2025-05-20T17:43:46+00:00