CVE-2025-66455 (GCVE-0-2025-66455)

Vulnerability from cvelistv5 – Published: 2026-09-18 17:03 – Updated: 2026-09-18 19:54
VLAI
Title
LMDeploy has Remote Code Execution by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.py
Summary
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.2 and prior to version 0.16.0, LMDeploy's PyTorch DistServe/PD-disaggregation control plane used `recv_pyobj()` to deserialize messages received through a ZeroMQ PULL socket. PyZMQ implements `recv_pyobj()` using Python pickle deserialization, which can execute arbitrary code while reconstructing an object. The peer address used by the receiver was supplied through the `POST /distserve/p2p_connect` HTTP endpoint. An attacker who could reach an affected DistServe API server could cause the server to connect to an attacker-controlled ZeroMQ endpoint and deserialize a crafted pickle payload. API-key authentication is not enabled unless the operator explicitly configures it. As a result, affected DistServe deployments without API keys allowed unauthenticated remote code execution with the privileges of the LMDeploy serving process. This issue affects the PyTorch backend when PD-disaggregation/DistServe is enabled. Ordinary deployments that do not use the affected disaggregated-serving path do not expose this data flow. The fix was released in LMDeploy 0.16.0. Users who cannot upgrade immediately should prevent untrusted clients from reaching `/distserve/*` endpoints, restrict the DistServe HTTP and ZeroMQ control planes to trusted cluster networks, configure API-key authentication, and block arbitrary outbound ZeroMQ connections from serving nodes. These measures reduce exposure but do not make pickle deserialization safe.
Severity
9.8 (Critical)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
SSVC
Exploitation: none Automatable: yes Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-09-18 19:54 UTC
CWE
  • CWE-502 - Deserialization of Untrusted Data
Assigner
GitHub_M CNA under the mitre root
CNA scorecard C 72/100 over 7627 records in the last 180 days details
References
Impacted products
Vendor Product Version CPE status
InternLM lmdeploy Affected: >= 0.9.2, < 0.16.0
guessed Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2025-66455",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-09-18T19:54:08.825899Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-09-18T19:54:19.941Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "lmdeploy",
          "vendor": "InternLM",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 0.9.2, \u003c 0.16.0"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.2 and prior to version 0.16.0, LMDeploy\u0027s PyTorch DistServe/PD-disaggregation control plane used `recv_pyobj()` to deserialize messages received through a ZeroMQ PULL socket. PyZMQ implements `recv_pyobj()` using Python pickle deserialization, which can execute arbitrary code while reconstructing an object. The peer address used by the receiver was supplied through the `POST /distserve/p2p_connect` HTTP endpoint. An attacker who could reach an affected DistServe API server could cause the server to connect to an attacker-controlled ZeroMQ endpoint and deserialize a crafted pickle payload. API-key authentication is not enabled unless the operator explicitly configures it. As a result, affected DistServe deployments without API keys allowed unauthenticated remote code execution with the privileges of the LMDeploy serving process. This issue affects the PyTorch backend when PD-disaggregation/DistServe is enabled. Ordinary deployments that do not use the affected disaggregated-serving path do not expose this data flow. The fix was released in LMDeploy 0.16.0. Users who cannot upgrade immediately should prevent untrusted clients from reaching `/distserve/*` endpoints, restrict the DistServe HTTP and ZeroMQ control planes to trusted cluster networks, configure API-key authentication, and block arbitrary outbound ZeroMQ connections from serving nodes. These measures reduce exposure but do not make pickle deserialization safe."
        }
      ],
      "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": "2026-09-18T17:03:37.084Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/InternLM/lmdeploy/security/advisories/GHSA-2vh9-42vm-xmv2",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/InternLM/lmdeploy/security/advisories/GHSA-2vh9-42vm-xmv2"
        },
        {
          "name": "https://github.com/InternLM/lmdeploy/commit/f05b4ad8bf2e2d84101a1d63b3c44fadd99223b2",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/InternLM/lmdeploy/commit/f05b4ad8bf2e2d84101a1d63b3c44fadd99223b2"
        },
        {
          "name": "https://github.com/InternLM/lmdeploy/releases/tag/v0.16.0",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/InternLM/lmdeploy/releases/tag/v0.16.0"
        }
      ],
      "source": {
        "advisory": "GHSA-2vh9-42vm-xmv2",
        "discovery": "UNKNOWN"
      },
      "title": "LMDeploy has Remote Code Execution\u00a0by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.py"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2025-66455",
    "datePublished": "2026-09-18T17:03:37.084Z",
    "dateReserved": "2025-12-01T18:44:35.640Z",
    "dateUpdated": "2026-09-18T19:54:19.941Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2025-66455",
      "date": "2026-10-19",
      "epss": "0.00693",
      "percentile": "0.52027"
    },
    "nvd": {
      "cve": {
        "affected": [
          {
            "affectedData": [
              {
                "product": "lmdeploy",
                "vendor": "InternLM",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003e= 0.9.2, \u003c 0.16.0"
                  }
                ]
              }
            ],
            "source": "security-advisories@github.com"
          }
        ],
        "cveTags": [],
        "descriptions": [
          {
            "lang": "en",
            "value": "LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.2 and prior to version 0.16.0, LMDeploy\u0027s PyTorch DistServe/PD-disaggregation control plane used `recv_pyobj()` to deserialize messages received through a ZeroMQ PULL socket. PyZMQ implements `recv_pyobj()` using Python pickle deserialization, which can execute arbitrary code while reconstructing an object. The peer address used by the receiver was supplied through the `POST /distserve/p2p_connect` HTTP endpoint. An attacker who could reach an affected DistServe API server could cause the server to connect to an attacker-controlled ZeroMQ endpoint and deserialize a crafted pickle payload. API-key authentication is not enabled unless the operator explicitly configures it. As a result, affected DistServe deployments without API keys allowed unauthenticated remote code execution with the privileges of the LMDeploy serving process. This issue affects the PyTorch backend when PD-disaggregation/DistServe is enabled. Ordinary deployments that do not use the affected disaggregated-serving path do not expose this data flow. The fix was released in LMDeploy 0.16.0. Users who cannot upgrade immediately should prevent untrusted clients from reaching `/distserve/*` endpoints, restrict the DistServe HTTP and ZeroMQ control planes to trusted cluster networks, configure API-key authentication, and block arbitrary outbound ZeroMQ connections from serving nodes. These measures reduce exposure but do not make pickle deserialization safe."
          },
          {
            "lang": "es",
            "value": "LMDeploy es un kit de herramientas para comprimir, desplegar y servir modelos de lenguaje grandes. A partir de la versi\u00f3n 0.9.2 y versiones anteriores a la versi\u00f3n 0.16.0, el plano de control PyTorch DistServe/PD-disaggregation de LMDeploy utilizaba \u0027recv_pyobj()\u0027 para deserializar mensajes recibidos a trav\u00e9s de un socket ZeroMQ PULL. PyZMQ implementa \u0027recv_pyobj()\u0027 utilizando la deserializaci\u00f3n de Python pickle, que puede ejecutar c\u00f3digo arbitrario al reconstruir un objeto. La direcci\u00f3n del par utilizada por el receptor se suministraba a trav\u00e9s del endpoint HTTP \u0027POST /distserve/p2p_connect\u0027. Un atacante que pudiera alcanzar un servidor API DistServe afectado podr\u00eda hacer que el servidor se conectara a un endpoint ZeroMQ controlado por el atacante y deserializara una carga \u00fatil pickle manipulada. La autenticaci\u00f3n con clave API no est\u00e1 habilitada a menos que el operador la configure expl\u00edcitamente. Como resultado, las implementaciones de DistServe afectadas sin claves API permit\u00edan la ejecuci\u00f3n remota de c\u00f3digo no autenticada con los privilegios del proceso de servicio de LMDeploy. Este problema afecta al backend de PyTorch cuando PD-disaggregation/DistServe est\u00e1 habilitado. Las implementaciones ordinarias que no utilizan la ruta de servicio desagregado afectada no exponen este flujo de datos. La correcci\u00f3n se lanz\u00f3 en LMDeploy 0.16.0. Los usuarios que no puedan actualizar de inmediato deben evitar que clientes no confiables accedan a los endpoints \u0027/distserve/*\u0027, restringir los planos de control HTTP y ZeroMQ de DistServe a redes de cl\u00faster confiables, configurar la autenticaci\u00f3n con clave API y bloquear las conexiones ZeroMQ salientes arbitrarias desde los nodos de servicio. Estas medidas reducen la exposici\u00f3n, pero no hacen que la deserializaci\u00f3n de pickle sea segura."
          }
        ],
        "id": "CVE-2025-66455",
        "lastModified": "2026-10-14T13:10:00.187",
        "metrics": {
          "cvssMetricV31": [
            {
              "cvssData": {
                "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"
              },
              "exploitabilityScore": 3.9,
              "impactScore": 5.9,
              "source": "security-advisories@github.com",
              "type": "Secondary"
            }
          ],
          "ssvcV203": [
            {
              "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "ssvcData": {
                "id": "CVE-2025-66455",
                "options": [
                  {
                    "exploitation": "none"
                  },
                  {
                    "automatable": "yes"
                  },
                  {
                    "technicalImpact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-09-18T19:54:08.825899Z",
                "version": "2.0.3"
              }
            }
          ]
        },
        "published": "2026-09-18T18:17:04.420",
        "references": [
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/InternLM/lmdeploy/commit/f05b4ad8bf2e2d84101a1d63b3c44fadd99223b2"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/InternLM/lmdeploy/releases/tag/v0.16.0"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/InternLM/lmdeploy/security/advisories/GHSA-2vh9-42vm-xmv2"
          }
        ],
        "sourceIdentifier": "security-advisories@github.com",
        "vulnStatus": "Awaiting Analysis",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-502"
              }
            ],
            "source": "security-advisories@github.com",
            "type": "Secondary"
          }
        ]
      }
    },
    "vulnrichment": {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2025-66455",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-18T19:54:08.825899Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-18T19:54:14.828Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "lmdeploy",
              "vendor": "InternLM",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 0.9.2, \u003c 0.16.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.2 and prior to version 0.16.0, LMDeploy\u0027s PyTorch DistServe/PD-disaggregation control plane used `recv_pyobj()` to deserialize messages received through a ZeroMQ PULL socket. PyZMQ implements `recv_pyobj()` using Python pickle deserialization, which can execute arbitrary code while reconstructing an object. The peer address used by the receiver was supplied through the `POST /distserve/p2p_connect` HTTP endpoint. An attacker who could reach an affected DistServe API server could cause the server to connect to an attacker-controlled ZeroMQ endpoint and deserialize a crafted pickle payload. API-key authentication is not enabled unless the operator explicitly configures it. As a result, affected DistServe deployments without API keys allowed unauthenticated remote code execution with the privileges of the LMDeploy serving process. This issue affects the PyTorch backend when PD-disaggregation/DistServe is enabled. Ordinary deployments that do not use the affected disaggregated-serving path do not expose this data flow. The fix was released in LMDeploy 0.16.0. Users who cannot upgrade immediately should prevent untrusted clients from reaching `/distserve/*` endpoints, restrict the DistServe HTTP and ZeroMQ control planes to trusted cluster networks, configure API-key authentication, and block arbitrary outbound ZeroMQ connections from serving nodes. These measures reduce exposure but do not make pickle deserialization safe."
            }
          ],
          "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": "2026-09-18T17:03:37.084Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/InternLM/lmdeploy/security/advisories/GHSA-2vh9-42vm-xmv2",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/InternLM/lmdeploy/security/advisories/GHSA-2vh9-42vm-xmv2"
            },
            {
              "name": "https://github.com/InternLM/lmdeploy/commit/f05b4ad8bf2e2d84101a1d63b3c44fadd99223b2",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/InternLM/lmdeploy/commit/f05b4ad8bf2e2d84101a1d63b3c44fadd99223b2"
            },
            {
              "name": "https://github.com/InternLM/lmdeploy/releases/tag/v0.16.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/InternLM/lmdeploy/releases/tag/v0.16.0"
            }
          ],
          "source": {
            "advisory": "GHSA-2vh9-42vm-xmv2",
            "discovery": "UNKNOWN"
          },
          "title": "LMDeploy has Remote Code Execution\u00a0by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.py"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2025-66455",
        "datePublished": "2026-09-18T17:03:37.084Z",
        "dateReserved": "2025-12-01T18:44:35.640Z",
        "dateUpdated": "2026-09-18T19:54:19.941Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.

Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

Sightings

Author Source Type Date Other

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.
Vulnerability timeline

Sightings and recorded dates, grouped by day · UTC

JSON

Loading timeline…




    Related by attack behaviour

    Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.