Vulnerability-Lookup

WID-SEC-W-2025-2883

Vulnerability from csaf_certbund - Published: 2025-12-18 23:00 - Updated: 2025-12-18 23:00

Summary

Red Hat Enterprise AI Inference Server (vLLM): Schwachstelle ermöglicht Codeausführung

Notes

Das BSI ist als Anbieter für die eigenen, zur Nutzung bereitgestellten Inhalte nach den allgemeinen Gesetzen verantwortlich. Nutzerinnen und Nutzer sind jedoch dafür verantwortlich, die Verwendung und/oder die Umsetzung der mit den Inhalten bereitgestellten Informationen sorgfältig im Einzelfall zu prüfen.

Produktbeschreibung

Red Hat Enterprise Linux (RHEL) ist eine populäre Linux-Distribution.

Angriff

Ein Angreifer aus einem angrenzenden Netzwerk kann eine Schwachstelle in Red Hat Enterprise AI Inference Server ausnutzen, um beliebigen Programmcode auszuführen.

Betroffene Betriebssysteme

- Linux

JSON

To clipboard

{
  "document": {
    "aggregate_severity": {
      "text": "mittel"
    },
    "category": "csaf_base",
    "csaf_version": "2.0",
    "distribution": {
      "tlp": {
        "label": "WHITE",
        "url": "https://www.first.org/tlp/"
      }
    },
    "lang": "de-DE",
    "notes": [
      {
        "category": "legal_disclaimer",
        "text": "Das BSI ist als Anbieter f\u00fcr die eigenen, zur Nutzung bereitgestellten Inhalte nach den allgemeinen Gesetzen verantwortlich. Nutzerinnen und Nutzer sind jedoch daf\u00fcr verantwortlich, die Verwendung und/oder die Umsetzung der mit den Inhalten bereitgestellten Informationen sorgf\u00e4ltig im Einzelfall zu pr\u00fcfen."
      },
      {
        "category": "description",
        "text": "Red Hat Enterprise Linux (RHEL) ist eine popul\u00e4re Linux-Distribution.",
        "title": "Produktbeschreibung"
      },
      {
        "category": "summary",
        "text": "Ein Angreifer aus einem angrenzenden Netzwerk kann eine Schwachstelle in Red Hat Enterprise AI Inference Server ausnutzen, um beliebigen Programmcode auszuf\u00fchren.",
        "title": "Angriff"
      },
      {
        "category": "general",
        "text": "- Linux",
        "title": "Betroffene Betriebssysteme"
      }
    ],
    "publisher": {
      "category": "other",
      "contact_details": "csaf-provider@cert-bund.de",
      "name": "Bundesamt f\u00fcr Sicherheit in der Informationstechnik",
      "namespace": "https://www.bsi.bund.de"
    },
    "references": [
      {
        "category": "self",
        "summary": "WID-SEC-W-2025-2883 - CSAF Version",
        "url": "https://wid.cert-bund.de/.well-known/csaf/white/2025/wid-sec-w-2025-2883.json"
      },
      {
        "category": "self",
        "summary": "WID-SEC-2025-2883 - Portal Version",
        "url": "https://wid.cert-bund.de/portal/wid/securityadvisory?name=WID-SEC-2025-2883"
      },
      {
        "category": "external",
        "summary": "RedHat Security Advisory vom 2025-12-18",
        "url": "https://access.redhat.com/errata/RHSA-2025:10404"
      },
      {
        "category": "external",
        "summary": "RedHat Security Advisory vom 2025-12-18",
        "url": "https://access.redhat.com/errata/RHSA-2025:10403"
      }
    ],
    "source_lang": "en-US",
    "title": "Red Hat Enterprise AI Inference Server (vLLM): Schwachstelle erm\u00f6glicht Codeausf\u00fchrung",
    "tracking": {
      "current_release_date": "2025-12-18T23:00:00.000+00:00",
      "generator": {
        "date": "2025-12-19T11:20:00.838+00:00",
        "engine": {
          "name": "BSI-WID",
          "version": "1.5.0"
        }
      },
      "id": "WID-SEC-W-2025-2883",
      "initial_release_date": "2025-12-18T23:00:00.000+00:00",
      "revision_history": [
        {
          "date": "2025-12-18T23:00:00.000+00:00",
          "number": "1",
          "summary": "Initiale Fassung"
        }
      ],
      "status": "final",
      "version": "1"
    }
  },
  "product_tree": {
    "branches": [
      {
        "branches": [
          {
            "branches": [
              {
                "category": "product_version_range",
                "name": "AI Inference Server (CUDA) \u003c3.0",
                "product": {
                  "name": "Red Hat Enterprise Linux AI Inference Server (CUDA) \u003c3.0",
                  "product_id": "T049556"
                }
              },
              {
                "category": "product_version",
                "name": "AI Inference Server (CUDA) 3.0",
                "product": {
                  "name": "Red Hat Enterprise Linux AI Inference Server (CUDA) 3.0",
                  "product_id": "T049556-fixed",
                  "product_identification_helper": {
                    "cpe": "cpe:/o:redhat:enterprise_linux:ai_inference_server_%2528cuda%2529__3.0"
                  }
                }
              },
              {
                "category": "product_version_range",
                "name": "AI Inference Server (ROCm) \u003c3.0",
                "product": {
                  "name": "Red Hat Enterprise Linux AI Inference Server (ROCm) \u003c3.0",
                  "product_id": "T049557"
                }
              },
              {
                "category": "product_version",
                "name": "AI Inference Server (ROCm) 3.0",
                "product": {
                  "name": "Red Hat Enterprise Linux AI Inference Server (ROCm) 3.0",
                  "product_id": "T049557-fixed",
                  "product_identification_helper": {
                    "cpe": "cpe:/o:redhat:enterprise_linux:ai_inference_server_%2528rocm%2529__3.0"
                  }
                }
              }
            ],
            "category": "product_name",
            "name": "Enterprise Linux"
          }
        ],
        "category": "vendor",
        "name": "Red Hat"
      }
    ]
  },
  "vulnerabilities": [
    {
      "cve": "CVE-2025-47277",
      "product_status": {
        "known_affected": [
          "T049557",
          "T049556"
        ]
      },
      "release_date": "2025-12-18T23:00:00.000+00:00",
      "title": "CVE-2025-47277"
    }
  ]
}

CVE-2025-47277 (GCVE-0-2025-47277)

Vulnerability from cvelistv5 – Published: 2025-05-20 17:32 – Updated: 2025-05-20 17:52

Title

vLLM Allows Remote Code Execution via PyNcclPipe Communication Service

Summary

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.

Severity ?

9.8 (Critical)


                        
                          CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

CWE

CWE-502 - Deserialization of Untrusted Data

Assigner

GitHub_M

References

URL

Tags

	https://github.com/vllm-project/vllm/security/adv…	x_refsource_CONFIRM
	https://github.com/vllm-project/vllm/pull/15988	x_refsource_MISC
	https://github.com/vllm-project/vllm/commit/0d6e1…	x_refsource_MISC
	https://docs.vllm.ai/en/latest/deployment/security.html	x_refsource_MISC

Impacted products

	Vendor	Product	Version
	vllm-project	vllm	Affected: >= 0.6.5, < 0.8.5

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2025-47277",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2025-05-20T17:52:22.643444Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2025-05-20T17:52:31.274Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 0.6.5, \u003c 0.8.5"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "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."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 9.8,
            "baseSeverity": "CRITICAL",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-502",
              "description": "CWE-502: Deserialization of Untrusted Data",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2025-05-20T17:32:27.034Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-hjq4-87xh-g4fv",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-hjq4-87xh-g4fv"
        },
        {
          "name": "https://github.com/vllm-project/vllm/pull/15988",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/15988"
        },
        {
          "name": "https://github.com/vllm-project/vllm/commit/0d6e187e88874c39cda7409cf673f9e6546893e7",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/commit/0d6e187e88874c39cda7409cf673f9e6546893e7"
        },
        {
          "name": "https://docs.vllm.ai/en/latest/deployment/security.html",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://docs.vllm.ai/en/latest/deployment/security.html"
        }
      ],
      "source": {
        "advisory": "GHSA-hjq4-87xh-g4fv",
        "discovery": "UNKNOWN"
      },
      "title": "vLLM Allows Remote Code Execution via PyNcclPipe Communication Service"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2025-47277",
    "datePublished": "2025-05-20T17:32:27.034Z",
    "dateReserved": "2025-05-05T16:53:10.373Z",
    "dateUpdated": "2025-05-20T17:52:31.274Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1"
}

Sightings

Author	Source	Type	Date

Nomenclature

Seen: The vulnerability was mentioned, discussed, or observed by the user.
Confirmed: The vulnerability has been validated from an analyst's perspective.
Published Proof of Concept: A public proof of concept is available for this vulnerability.
Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
Not confirmed: The user expressed doubt about the validity of the vulnerability.
Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.

Detection rules are retrieved from Rulezet.

Action not permitted

WID-SEC-W-2025-2883

CVE-2025-47277 (GCVE-0-2025-47277)

Tags

Sightings

Nomenclature