CVE-2026-48121 (GCVE-0-2026-48121)

Vulnerability from cvelistv5 – Published: 2026-08-04 16:49 – Updated: 2026-08-04 19:51
VLAI
Title
@langchain/langgraph-checkpoint-mongodb: NoSQL parameter injection in MongoDBSaver allows cross-tenant state access
Summary
@langchain/langgraph-checkpoint-mongodb provides a LangGraph.js CheckpointSaver implementation that uses MongoDB for storage. Versions 1.3.0 and below are vulnerable to NoSQL injection: checkpoint identifiers (thread_id, checkpoint_ns, checkpoint_id) from config.configurable are passed into MongoDB find() queries in MongoDBSaver.getTuple() without type enforcement. If an attacker supplies an object payload (such as MongoDB operators $gt or $ne) instead of a string, it can be interpreted as a query operator, bypassing thread scoping and leaking checkpoints, including pending writes, across tenants. Applications are at risk if they forward untrusted input into config.configurable without coercing it to strings or validating it against a schema, particularly in multi-tenant or user-isolated setups. Apps that only use server-issued, string-typed identifiers with schema validation rejecting non-string fields are not affected. This issue has been fixed in version 1.3.1.
SSVC
Exploitation: none Automatable: no Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-08-04 19:15 UTC
CWE
  • CWE-943 - Improper Neutralization of Special Elements in Data Query Logic
Assigner
GitHub_M CNA under the mitre root
CNA scorecard C 72/100 over 8156 records in the last 180 days details
Impacted products
Vendor Product Version CPE status
langchain-ai langgraphjs Affected: < 1.3.1
guessed Create a notification for this product.
Show details on NVD website

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-48121",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-04T19:15:56.587064Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-08-04T19:51:50.111Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "langgraphjs",
          "vendor": "langchain-ai",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 1.3.1"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "@langchain/langgraph-checkpoint-mongodb provides a LangGraph.js CheckpointSaver implementation that uses MongoDB for storage. Versions 1.3.0 and below are vulnerable to NoSQL injection: checkpoint identifiers (thread_id, checkpoint_ns, checkpoint_id) from config.configurable are passed into MongoDB find() queries in MongoDBSaver.getTuple() without type enforcement. If an attacker supplies an object payload (such as MongoDB operators $gt or $ne) instead of a string, it can be interpreted as a query operator, bypassing thread scoping and leaking checkpoints, including pending writes, across tenants. Applications are at risk if they forward untrusted input into config.configurable without coercing it to strings or validating it against a schema, particularly in multi-tenant or user-isolated setups. Apps that only use server-issued, string-typed identifiers with schema validation rejecting non-string fields are not affected. This issue has been fixed in version 1.3.1."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "ADJACENT_NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 6.7,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:A/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-943",
              "description": "CWE-943: Improper Neutralization of Special Elements in Data Query Logic",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-08-04T16:49:57.680Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/langchain-ai/langgraphjs/security/advisories/GHSA-98xf-r82g-9mhx",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/langchain-ai/langgraphjs/security/advisories/GHSA-98xf-r82g-9mhx"
        },
        {
          "name": "https://github.com/langchain-ai/langgraphjs/issues/2351",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/langchain-ai/langgraphjs/issues/2351"
        },
        {
          "name": "https://github.com/langchain-ai/langgraphjs/commit/284226c7ca164b3c81fe2d9e32b10f1fc6b99a3c",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/langchain-ai/langgraphjs/commit/284226c7ca164b3c81fe2d9e32b10f1fc6b99a3c"
        }
      ],
      "source": {
        "advisory": "GHSA-98xf-r82g-9mhx",
        "discovery": "UNKNOWN"
      },
      "title": "@langchain/langgraph-checkpoint-mongodb: NoSQL parameter injection in MongoDBSaver allows cross-tenant state access"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-48121",
    "datePublished": "2026-08-04T16:49:57.680Z",
    "dateReserved": "2026-05-20T18:46:58.290Z",
    "dateUpdated": "2026-08-04T19:51:50.111Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-48121",
      "date": "2026-11-21",
      "epss": "0.00313",
      "percentile": "0.24602"
    },
    "nvd": {
      "cve": {
        "affected": [
          {
            "affectedData": [
              {
                "product": "langgraphjs",
                "vendor": "langchain-ai",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003c 1.3.1"
                  }
                ]
              }
            ],
            "source": "security-advisories@github.com"
          }
        ],
        "cveTags": [],
        "descriptions": [
          {
            "lang": "en",
            "value": "@langchain/langgraph-checkpoint-mongodb provides a LangGraph.js CheckpointSaver implementation that uses MongoDB for storage. Versions 1.3.0 and below are vulnerable to NoSQL injection: checkpoint identifiers (thread_id, checkpoint_ns, checkpoint_id) from config.configurable are passed into MongoDB find() queries in MongoDBSaver.getTuple() without type enforcement. If an attacker supplies an object payload (such as MongoDB operators $gt or $ne) instead of a string, it can be interpreted as a query operator, bypassing thread scoping and leaking checkpoints, including pending writes, across tenants. Applications are at risk if they forward untrusted input into config.configurable without coercing it to strings or validating it against a schema, particularly in multi-tenant or user-isolated setups. Apps that only use server-issued, string-typed identifiers with schema validation rejecting non-string fields are not affected. This issue has been fixed in version 1.3.1."
          },
          {
            "lang": "es",
            "value": "Langchain/langgraph-checkpoint-mongodb proporciona una implementaci\u00f3n de CheckpointSaver de LangGraph.js que utiliza MongoDB para el almacenamiento. Las versiones 1.3.0 e inferiores son vulnerables a la inyecci\u00f3n NoSQL: los identificadores de punto de control (thread_id, checkpoint_ns, checkpoint_id) de config.configurable se pasan a las consultas find() de MongoDB en MongoDBSaver.getTuple() sin aplicaci\u00f3n de tipo. Si un atacante suministra una carga \u00fatil de objeto (como los operadores de MongoDB $gt o $ne) en lugar de una cadena, puede interpretarse como un operador de consulta, eludiendo el alcance del hilo y filtrando puntos de control, incluidas las escrituras pendientes, entre inquilinos. Las aplicaciones est\u00e1n en riesgo si reenv\u00edan entradas no confiables a config.configurable sin convertirlas a cadenas o validarlas contra un esquema, particularmente en configuraciones multiinquilino o aisladas por usuario. Las aplicaciones que solo usan identificadores de tipo cadena emitidos por el servidor con validaci\u00f3n de esquema que rechaza campos que no son cadenas no se ven afectadas. Este problema ha sido solucionado en la versi\u00f3n 1.3.1."
          }
        ],
        "id": "CVE-2026-48121",
        "lastModified": "2026-10-24T16:10:00.153",
        "metrics": {
          "cvssMetricV31": [
            {
              "cvssData": {
                "attackComplexity": "LOW",
                "attackVector": "ADJACENT_NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 6.7,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "REQUIRED",
                "vectorString": "CVSS:3.1/AV:A/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N",
                "version": "3.1"
              },
              "exploitabilityScore": 1.5,
              "impactScore": 5.2,
              "source": "security-advisories@github.com",
              "type": "Secondary"
            }
          ],
          "ssvcV203": [
            {
              "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "ssvcData": {
                "id": "CVE-2026-48121",
                "options": [
                  {
                    "exploitation": "none"
                  },
                  {
                    "automatable": "no"
                  },
                  {
                    "technicalImpact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-04T19:15:56.587064Z",
                "version": "2.0.3"
              }
            }
          ]
        },
        "published": "2026-08-04T17:16:55.267",
        "references": [
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/langchain-ai/langgraphjs/commit/284226c7ca164b3c81fe2d9e32b10f1fc6b99a3c"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/langchain-ai/langgraphjs/issues/2351"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/langchain-ai/langgraphjs/security/advisories/GHSA-98xf-r82g-9mhx"
          }
        ],
        "sourceIdentifier": "security-advisories@github.com",
        "vulnStatus": "Awaiting Analysis",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-943"
              }
            ],
            "source": "security-advisories@github.com",
            "type": "Secondary"
          }
        ]
      }
    },
    "vulnrichment": {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-48121",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-08-04T19:15:56.587064Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-08-04T19:16:00.559Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "langgraphjs",
              "vendor": "langchain-ai",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 1.3.1"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "@langchain/langgraph-checkpoint-mongodb provides a LangGraph.js CheckpointSaver implementation that uses MongoDB for storage. Versions 1.3.0 and below are vulnerable to NoSQL injection: checkpoint identifiers (thread_id, checkpoint_ns, checkpoint_id) from config.configurable are passed into MongoDB find() queries in MongoDBSaver.getTuple() without type enforcement. If an attacker supplies an object payload (such as MongoDB operators $gt or $ne) instead of a string, it can be interpreted as a query operator, bypassing thread scoping and leaking checkpoints, including pending writes, across tenants. Applications are at risk if they forward untrusted input into config.configurable without coercing it to strings or validating it against a schema, particularly in multi-tenant or user-isolated setups. Apps that only use server-issued, string-typed identifiers with schema validation rejecting non-string fields are not affected. This issue has been fixed in version 1.3.1."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "ADJACENT_NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 6.7,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "REQUIRED",
                "vectorString": "CVSS:3.1/AV:A/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-943",
                  "description": "CWE-943: Improper Neutralization of Special Elements in Data Query Logic",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-08-04T16:49:57.680Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/langchain-ai/langgraphjs/security/advisories/GHSA-98xf-r82g-9mhx",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/langchain-ai/langgraphjs/security/advisories/GHSA-98xf-r82g-9mhx"
            },
            {
              "name": "https://github.com/langchain-ai/langgraphjs/issues/2351",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/langchain-ai/langgraphjs/issues/2351"
            },
            {
              "name": "https://github.com/langchain-ai/langgraphjs/commit/284226c7ca164b3c81fe2d9e32b10f1fc6b99a3c",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/langchain-ai/langgraphjs/commit/284226c7ca164b3c81fe2d9e32b10f1fc6b99a3c"
            }
          ],
          "source": {
            "advisory": "GHSA-98xf-r82g-9mhx",
            "discovery": "UNKNOWN"
          },
          "title": "@langchain/langgraph-checkpoint-mongodb: NoSQL parameter injection in MongoDBSaver allows cross-tenant state access"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-48121",
        "datePublished": "2026-08-04T16:49:57.680Z",
        "dateReserved": "2026-05-20T18:46:58.290Z",
        "dateUpdated": "2026-08-04T19:51:50.111Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.


Loading…

Loading…

Loading…

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
How durations are calculated

Following the VTEM framework (Black Hat USA 2015), time to patch starts when the vendor or a coordinator was informed, total time to patch at discovery, and disclosure to patch at public disclosure; vendor response time runs from the report to its acknowledgement. Time to exploit and time unpatched start at the earliest discovery or report, falling back to public disclosure. Unpatched time ends at the first recorded patch, or the calculation time when no patch is recorded. Exploitation to patch shows the interval between those two events; a published proof of concept is a public exploit, not exploitation.

Each result shows its source dates. A negative interval means the end event came first; when date-only inputs leave the order open, the result says so. Date-only inputs are approximate. The earliest evidence wins: KEV report dates and sightings are labelled as such. Records describing another vulnerability are listed but never calculated from, and a PoC alone does not establish exploitation. Missing patch evidence does not prove that no patch exists. Filters below change the event list only.

Events included in the timeline

Loading timeline…


    Loading…

    Loading…

    Loading…

    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.