CVE-2026-44843 (GCVE-0-2026-44843)

Vulnerability from cvelistv5 – Published: 2026-05-26 19:47 – Updated: 2026-05-27 14:07
VLAI
Title
LangChain: Unsafe deserialization of attacker-controlled LangChain objects through overly broad `load()` allowlists
Summary
LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.85 and 1.3.3, LangChain contains older runtime code paths that deserialize run inputs, run outputs, or other application-controlled payloads using overly broad object allowlists. These paths may call load() with allowed_objects="all". This does not enable arbitrary Python object deserialization, but it does allow any trusted LangChain-serializable object to be revived, which is broader than these runtime paths require. As a result, attacker-supplied LangChain serialized constructor dictionaries may cause trusted runtime paths to instantiate classes with untrusted constructor arguments. This vulnerability is fixed in 0.3.85 and 1.3.3.
Severity
8.2 (High)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N
SSVC
Exploitation: none Automatable: yes Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-05-27 14:06 UTC
CWE
  • CWE-502 - Deserialization of Untrusted Data
Assigner
GitHub_M CNA under the mitre root
CNA scorecard C 72/100 over 7886 records in the last 180 days details
References
Impacted products
Vendor Product Version CPE status
langchain-ai langchain Affected: < 0.3.85
Affected: >= 1.0.0a1, < 1.3.3
guessed Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-44843",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-05-27T14:06:50.805026Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-05-27T14:07:03.564Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "langchain",
          "vendor": "langchain-ai",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.3.85"
            },
            {
              "status": "affected",
              "version": "\u003e= 1.0.0a1, \u003c 1.3.3"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.85 and 1.3.3, LangChain contains older runtime code paths that deserialize run inputs, run outputs, or other application-controlled payloads using overly broad object allowlists. These paths may call load() with allowed_objects=\"all\". This does not enable arbitrary Python object deserialization, but it does allow any trusted LangChain-serializable object to be revived, which is broader than these runtime paths require. As a result, attacker-supplied LangChain serialized constructor dictionaries may cause trusted runtime paths to instantiate classes with untrusted constructor arguments. This vulnerability is fixed in 0.3.85 and 1.3.3."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 8.2,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "LOW",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-502",
              "description": "CWE-502: Deserialization of Untrusted Data",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-05-26T19:47:35.328Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-pjwx-r37v-7724",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-pjwx-r37v-7724"
        }
      ],
      "source": {
        "advisory": "GHSA-pjwx-r37v-7724",
        "discovery": "UNKNOWN"
      },
      "title": "LangChain: Unsafe deserialization of attacker-controlled LangChain objects through overly broad `load()` allowlists"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-44843",
    "datePublished": "2026-05-26T19:47:35.328Z",
    "dateReserved": "2026-05-07T21:21:48.352Z",
    "dateUpdated": "2026-05-27T14:07:03.564Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-44843",
      "date": "2026-11-13",
      "epss": "0.00406",
      "percentile": "0.35404"
    },
    "nvd": {
      "cve": {
        "affected": [
          {
            "affectedData": [
              {
                "product": "langchain",
                "vendor": "langchain-ai",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003c 0.3.85"
                  },
                  {
                    "status": "affected",
                    "version": "\u003e= 1.0.0a1, \u003c 1.3.3"
                  }
                ]
              }
            ],
            "source": "security-advisories@github.com"
          }
        ],
        "configurations": [
          {
            "nodes": [
              {
                "cpeMatch": [
                  {
                    "criteria": "cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*",
                    "matchCriteriaId": "F51597F7-5582-4105-8A1A-957ED4394741",
                    "versionEndExcluding": "0.3.85",
                    "vulnerable": true
                  },
                  {
                    "criteria": "cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*",
                    "matchCriteriaId": "ADE91EFB-2D03-4922-8089-5B34BD1DC348",
                    "versionEndExcluding": "1.3.3",
                    "versionStartIncluding": "1.0.0",
                    "vulnerable": true
                  }
                ],
                "negate": false,
                "operator": "OR"
              }
            ]
          }
        ],
        "cveTags": [],
        "descriptions": [
          {
            "lang": "en",
            "value": "LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.85 and 1.3.3, LangChain contains older runtime code paths that deserialize run inputs, run outputs, or other application-controlled payloads using overly broad object allowlists. These paths may call load() with allowed_objects=\"all\". This does not enable arbitrary Python object deserialization, but it does allow any trusted LangChain-serializable object to be revived, which is broader than these runtime paths require. As a result, attacker-supplied LangChain serialized constructor dictionaries may cause trusted runtime paths to instantiate classes with untrusted constructor arguments. This vulnerability is fixed in 0.3.85 and 1.3.3."
          },
          {
            "lang": "es",
            "value": "LangChain es un framework para construir agentes y aplicaciones impulsadas por LLM. Antes de 0.3.85 y 1.3.3, LangChain contiene rutas de c\u00f3digo de tiempo de ejecuci\u00f3n m\u00e1s antiguas que deserializan entradas de ejecuci\u00f3n, salidas de ejecuci\u00f3n u otras cargas \u00fatiles controladas por la aplicaci\u00f3n utilizando listas de permitidos de objetos excesivamente amplias. Estas rutas pueden llamar a load() con allowed_objects=\u0027all\u0027. Esto no habilita la deserializaci\u00f3n arbitraria de objetos Python, pero s\u00ed permite que cualquier objeto LangChain serializable de confianza sea revivido, lo cual es m\u00e1s amplio de lo que requieren estas rutas de tiempo de ejecuci\u00f3n. Como resultado, los diccionarios de constructor serializados de LangChain suministrados por el atacante pueden hacer que las rutas de tiempo de ejecuci\u00f3n de confianza instancien clases con argumentos de constructor no confiables. Esta vulnerabilidad est\u00e1 corregida en 0.3.85 y 1.3.3."
          }
        ],
        "id": "CVE-2026-44843",
        "lastModified": "2026-07-24T11:10:00.170",
        "metrics": {
          "cvssMetricV31": [
            {
              "cvssData": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 8.2,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "LOW",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N",
                "version": "3.1"
              },
              "exploitabilityScore": 3.9,
              "impactScore": 4.2,
              "source": "security-advisories@github.com",
              "type": "Secondary"
            }
          ],
          "ssvcV203": [
            {
              "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "ssvcData": {
                "id": "CVE-2026-44843",
                "options": [
                  {
                    "exploitation": "none"
                  },
                  {
                    "automatable": "yes"
                  },
                  {
                    "technicalImpact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-05-27T14:06:50.805026Z",
                "version": "2.0.3"
              }
            }
          ]
        },
        "published": "2026-05-26T21:16:39.003",
        "references": [
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Mitigation",
              "Vendor Advisory"
            ],
            "url": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-pjwx-r37v-7724"
          }
        ],
        "sourceIdentifier": "security-advisories@github.com",
        "vulnStatus": "Analyzed",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-502"
              }
            ],
            "source": "security-advisories@github.com",
            "type": "Secondary"
          }
        ]
      }
    },
    "redhat_vex": {
      "aggregate_severity": "Important",
      "current_release_date": "2026-10-19T11:17:22+00:00",
      "cve": "CVE-2026-44843",
      "id": "CVE-2026-44843",
      "initial_release_date": "2026-05-26T19:47:35.328000+00:00",
      "product_status:fixed": "18",
      "product_status:known_affected": "9",
      "product_status:known_not_affected": "886",
      "source": "Red Hat CSAF VEX",
      "status": "final",
      "title": "langchain: LangChain: Information disclosure and data integrity compromise via insecure deserialization",
      "url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-44843.json",
      "version": "3"
    },
    "vulnrichment": {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-44843",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-05-27T14:06:50.805026Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-05-27T14:06:57.825Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "langchain",
              "vendor": "langchain-ai",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.3.85"
                },
                {
                  "status": "affected",
                  "version": "\u003e= 1.0.0a1, \u003c 1.3.3"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.85 and 1.3.3, LangChain contains older runtime code paths that deserialize run inputs, run outputs, or other application-controlled payloads using overly broad object allowlists. These paths may call load() with allowed_objects=\"all\". This does not enable arbitrary Python object deserialization, but it does allow any trusted LangChain-serializable object to be revived, which is broader than these runtime paths require. As a result, attacker-supplied LangChain serialized constructor dictionaries may cause trusted runtime paths to instantiate classes with untrusted constructor arguments. This vulnerability is fixed in 0.3.85 and 1.3.3."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 8.2,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "LOW",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-502",
                  "description": "CWE-502: Deserialization of Untrusted Data",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-05-26T19:47:35.328Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-pjwx-r37v-7724",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-pjwx-r37v-7724"
            }
          ],
          "source": {
            "advisory": "GHSA-pjwx-r37v-7724",
            "discovery": "UNKNOWN"
          },
          "title": "LangChain: Unsafe deserialization of attacker-controlled LangChain objects through overly broad `load()` allowlists"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-44843",
        "datePublished": "2026-05-26T19:47:35.328Z",
        "dateReserved": "2026-05-07T21:21:48.352Z",
        "dateUpdated": "2026-05-27T14:07:03.564Z",
        "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
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.

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.