CVE-2024-28088
Vulnerability from cvelistv5
Published
2024-03-03 00:00
Modified
2024-08-26 19:44
Severity ?
8.1 (High) - CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N
Summary
LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a load_chain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub repository. The outcome can be disclosure of an API key for a large language model online service, or remote code execution. (A patch is available as of release 0.1.29 of langchain-core.)
References
cve@mitre.orghttps://github.com/PinkDraconian/PoC-Langchain-RCE/blob/main/README.mdExploit
cve@mitre.orghttps://github.com/langchain-ai/langchain/blob/f96dd57501131840b713ed7c2e86cbf1ddc2761f/libs/core/langchain_core/utils/loading.pyProduct, Third Party Advisory
cve@mitre.orghttps://github.com/langchain-ai/langchain/pull/18600Exploit, Issue Tracking, Patch
af854a3a-2127-422b-91ae-364da2661108https://github.com/PinkDraconian/PoC-Langchain-RCE/blob/main/README.mdExploit, Third Party Advisory
af854a3a-2127-422b-91ae-364da2661108https://github.com/langchain-ai/langchain/blob/f96dd57501131840b713ed7c2e86cbf1ddc2761f/libs/core/langchain_core/utils/loading.pyProduct
af854a3a-2127-422b-91ae-364da2661108https://github.com/langchain-ai/langchain/pull/18600Exploit, Issue Tracking, Patch
Impacted products
Vendor Product Version
n/a n/a Version: n/a
Show details on NVD website

To clipboard 

{
  "containers": {
    "adp": [
      {
        "providerMetadata": {
          "dateUpdated": "2024-08-02T00:48:48.940Z",
          "orgId": "af854a3a-2127-422b-91ae-364da2661108",
          "shortName": "CVE"
        },
        "references": [
          {
            "tags": [
              "x_transferred"
            ],
            "url": "https://github.com/PinkDraconian/PoC-Langchain-RCE/blob/main/README.md"
          },
          {
            "tags": [
              "x_transferred"
            ],
            "url": "https://github.com/langchain-ai/langchain/blob/f96dd57501131840b713ed7c2e86cbf1ddc2761f/libs/core/langchain_core/utils/loading.py"
          },
          {
            "tags": [
              "x_transferred"
            ],
            "url": "https://github.com/langchain-ai/langchain/pull/18600"
          }
        ],
        "title": "CVE Program Container"
      },
      {
        "affected": [
          {
            "cpes": [
              "cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*"
            ],
            "defaultStatus": "unknown",
            "product": "langchain",
            "vendor": "langchain",
            "versions": [
              {
                "lessThanOrEqual": "0.1.10",
                "status": "affected",
                "version": "0",
                "versionType": "custom"
              }
            ]
          }
        ],
        "metrics": [
          {
            "cvssV3_1": {
              "attackComplexity": "LOW",
              "attackVector": "NETWORK",
              "availabilityImpact": "NONE",
              "baseScore": 8.1,
              "baseSeverity": "HIGH",
              "confidentialityImpact": "HIGH",
              "integrityImpact": "HIGH",
              "privilegesRequired": "LOW",
              "scope": "UNCHANGED",
              "userInteraction": "NONE",
              "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N",
              "version": "3.1"
            }
          },
          {
            "other": {
              "content": {
                "id": "CVE-2024-28088",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2024-03-07T19:36:26.136405Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "problemTypes": [
          {
            "descriptions": [
              {
                "cweId": "CWE-31",
                "description": "CWE-31 Path Traversal: \u0027dir\\..\\..\\filename\u0027",
                "lang": "en",
                "type": "CWE"
              }
            ]
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2024-08-26T19:44:45.330Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "n/a",
          "vendor": "n/a",
          "versions": [
            {
              "status": "affected",
              "version": "n/a"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a load_chain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub repository. The outcome can be disclosure of an API key for a large language model online service, or remote code execution. (A patch is available as of release 0.1.29 of langchain-core.)"
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "description": "n/a",
              "lang": "en",
              "type": "text"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2024-03-13T21:00:45.400995",
        "orgId": "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
        "shortName": "mitre"
      },
      "references": [
        {
          "url": "https://github.com/PinkDraconian/PoC-Langchain-RCE/blob/main/README.md"
        },
        {
          "url": "https://github.com/langchain-ai/langchain/blob/f96dd57501131840b713ed7c2e86cbf1ddc2761f/libs/core/langchain_core/utils/loading.py"
        },
        {
          "url": "https://github.com/langchain-ai/langchain/pull/18600"
        }
      ]
    }
  },
  "cveMetadata": {
    "assignerOrgId": "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
    "assignerShortName": "mitre",
    "cveId": "CVE-2024-28088",
    "datePublished": "2024-03-03T00:00:00",
    "dateReserved": "2024-03-03T00:00:00",
    "dateUpdated": "2024-08-26T19:44:45.330Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1",
  "vulnerability-lookup:meta": {
    "fkie_nvd": {
      "configurations": "[{\"nodes\": [{\"operator\": \"OR\", \"negate\": false, \"cpeMatch\": [{\"vulnerable\": true, \"criteria\": \"cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*\", \"versionEndExcluding\": \"0.1.12\", \"matchCriteriaId\": \"2B206DB1-7431-4A55-A5E9-C6B29426AF56\"}]}]}]",
      "descriptions": "[{\"lang\": \"en\", \"value\": \"LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a load_chain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub repository. The outcome can be disclosure of an API key for a large language model online service, or remote code execution. (A patch is available as of release 0.1.29 of langchain-core.)\"}, {\"lang\": \"es\", \"value\": \"LangChain hasta 0.1.10 permite el Directory Traversal ../ por parte de un actor que puede controlar la parte final del par\\u00e1metro de ruta en una llamada load_chain. Esto omite el comportamiento previsto de cargar configuraciones solo desde el repositorio GitHub hwchase17/langchain-hub. El resultado puede ser la divulgaci\\u00f3n de una clave API para un servicio en l\\u00ednea de modelo de lenguaje grande o la ejecuci\\u00f3n remota de c\\u00f3digo.\"}]",
      "id": "CVE-2024-28088",
      "lastModified": "2025-01-08T16:13:57.860",
      "metrics": "{\"cvssMetricV31\": [{\"source\": \"nvd@nist.gov\", \"type\": \"Primary\", \"cvssData\": {\"version\": \"3.1\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N\", \"baseScore\": 8.1, \"baseSeverity\": \"HIGH\", \"attackVector\": \"NETWORK\", \"attackComplexity\": \"LOW\", \"privilegesRequired\": \"LOW\", \"userInteraction\": \"NONE\", \"scope\": \"UNCHANGED\", \"confidentialityImpact\": \"HIGH\", \"integrityImpact\": \"HIGH\", \"availabilityImpact\": \"NONE\"}, \"exploitabilityScore\": 2.8, \"impactScore\": 5.2}, {\"source\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"type\": \"Secondary\", \"cvssData\": {\"version\": \"3.1\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N\", \"baseScore\": 8.1, \"baseSeverity\": \"HIGH\", \"attackVector\": \"NETWORK\", \"attackComplexity\": \"LOW\", \"privilegesRequired\": \"LOW\", \"userInteraction\": \"NONE\", \"scope\": \"UNCHANGED\", \"confidentialityImpact\": \"HIGH\", \"integrityImpact\": \"HIGH\", \"availabilityImpact\": \"NONE\"}, \"exploitabilityScore\": 2.8, \"impactScore\": 5.2}]}",
      "published": "2024-03-04T00:15:47.017",
      "references": "[{\"url\": \"https://github.com/PinkDraconian/PoC-Langchain-RCE/blob/main/README.md\", \"source\": \"cve@mitre.org\", \"tags\": [\"Exploit\"]}, {\"url\": \"https://github.com/langchain-ai/langchain/blob/f96dd57501131840b713ed7c2e86cbf1ddc2761f/libs/core/langchain_core/utils/loading.py\", \"source\": \"cve@mitre.org\", \"tags\": [\"Product\", \"Third Party Advisory\"]}, {\"url\": \"https://github.com/langchain-ai/langchain/pull/18600\", \"source\": \"cve@mitre.org\", \"tags\": [\"Exploit\", \"Issue Tracking\", \"Patch\"]}, {\"url\": \"https://github.com/PinkDraconian/PoC-Langchain-RCE/blob/main/README.md\", \"source\": \"af854a3a-2127-422b-91ae-364da2661108\", \"tags\": [\"Exploit\", \"Third Party Advisory\"]}, {\"url\": \"https://github.com/langchain-ai/langchain/blob/f96dd57501131840b713ed7c2e86cbf1ddc2761f/libs/core/langchain_core/utils/loading.py\", \"source\": \"af854a3a-2127-422b-91ae-364da2661108\", \"tags\": [\"Product\"]}, {\"url\": \"https://github.com/langchain-ai/langchain/pull/18600\", \"source\": \"af854a3a-2127-422b-91ae-364da2661108\", \"tags\": [\"Exploit\", \"Issue Tracking\", \"Patch\"]}]",
      "sourceIdentifier": "cve@mitre.org",
      "vulnStatus": "Analyzed",
      "weaknesses": "[{\"source\": \"nvd@nist.gov\", \"type\": \"Primary\", \"description\": [{\"lang\": \"en\", \"value\": \"CWE-22\"}]}, {\"source\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"type\": \"Secondary\", \"description\": [{\"lang\": \"en\", \"value\": \"CWE-31\"}]}]"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2024-28088\",\"sourceIdentifier\":\"cve@mitre.org\",\"published\":\"2024-03-04T00:15:47.017\",\"lastModified\":\"2025-01-08T16:13:57.860\",\"vulnStatus\":\"Analyzed\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a load_chain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub repository. The outcome can be disclosure of an API key for a large language model online service, or remote code execution. (A patch is available as of release 0.1.29 of langchain-core.)\"},{\"lang\":\"es\",\"value\":\"LangChain hasta 0.1.10 permite el Directory Traversal ../ por parte de un actor que puede controlar la parte final del par\u00e1metro de ruta en una llamada load_chain. Esto omite el comportamiento previsto de cargar configuraciones solo desde el repositorio GitHub hwchase17/langchain-hub. El resultado puede ser la divulgaci\u00f3n de una clave API para un servicio en l\u00ednea de modelo de lenguaje grande o la ejecuci\u00f3n remota de c\u00f3digo.\"}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"nvd@nist.gov\",\"type\":\"Primary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N\",\"baseScore\":8.1,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":2.8,\"impactScore\":5.2},{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N\",\"baseScore\":8.1,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":2.8,\"impactScore\":5.2}]},\"weaknesses\":[{\"source\":\"nvd@nist.gov\",\"type\":\"Primary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-22\"}]},{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-31\"}]}],\"configurations\":[{\"nodes\":[{\"operator\":\"OR\",\"negate\":false,\"cpeMatch\":[{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*\",\"versionEndExcluding\":\"0.1.12\",\"matchCriteriaId\":\"2B206DB1-7431-4A55-A5E9-C6B29426AF56\"}]}]}],\"references\":[{\"url\":\"https://github.com/PinkDraconian/PoC-Langchain-RCE/blob/main/README.md\",\"source\":\"cve@mitre.org\",\"tags\":[\"Exploit\"]},{\"url\":\"https://github.com/langchain-ai/langchain/blob/f96dd57501131840b713ed7c2e86cbf1ddc2761f/libs/core/langchain_core/utils/loading.py\",\"source\":\"cve@mitre.org\",\"tags\":[\"Product\",\"Third Party Advisory\"]},{\"url\":\"https://github.com/langchain-ai/langchain/pull/18600\",\"source\":\"cve@mitre.org\",\"tags\":[\"Exploit\",\"Issue Tracking\",\"Patch\"]},{\"url\":\"https://github.com/PinkDraconian/PoC-Langchain-RCE/blob/main/README.md\",\"source\":\"af854a3a-2127-422b-91ae-364da2661108\",\"tags\":[\"Exploit\",\"Third Party Advisory\"]},{\"url\":\"https://github.com/langchain-ai/langchain/blob/f96dd57501131840b713ed7c2e86cbf1ddc2761f/libs/core/langchain_core/utils/loading.py\",\"source\":\"af854a3a-2127-422b-91ae-364da2661108\",\"tags\":[\"Product\"]},{\"url\":\"https://github.com/langchain-ai/langchain/pull/18600\",\"source\":\"af854a3a-2127-422b-91ae-364da2661108\",\"tags\":[\"Exploit\",\"Issue Tracking\",\"Patch\"]}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CVE Program Container\", \"references\": [{\"url\": \"https://github.com/PinkDraconian/PoC-Langchain-RCE/blob/main/README.md\", \"tags\": [\"x_transferred\"]}, {\"url\": \"https://github.com/langchain-ai/langchain/blob/f96dd57501131840b713ed7c2e86cbf1ddc2761f/libs/core/langchain_core/utils/loading.py\", \"tags\": [\"x_transferred\"]}, {\"url\": \"https://github.com/langchain-ai/langchain/pull/18600\", \"tags\": [\"x_transferred\"]}], \"providerMetadata\": {\"orgId\": \"af854a3a-2127-422b-91ae-364da2661108\", \"shortName\": \"CVE\", \"dateUpdated\": \"2024-08-02T00:48:48.940Z\"}}, {\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 8.1, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"NONE\", \"privilegesRequired\": \"LOW\", \"confidentialityImpact\": \"HIGH\"}}, {\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2024-28088\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2024-03-07T19:36:26.136405Z\"}}}], \"affected\": [{\"cpes\": [\"cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*\"], \"vendor\": \"langchain\", \"product\": \"langchain\", \"versions\": [{\"status\": \"affected\", \"version\": \"0\", \"versionType\": \"custom\", \"lessThanOrEqual\": \"0.1.10\"}], \"defaultStatus\": \"unknown\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-31\", \"description\": \"CWE-31 Path Traversal: \u0027dir\\\\..\\\\..\\\\filename\u0027\"}]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2024-08-26T19:43:28.326Z\"}}], \"cna\": {\"affected\": [{\"vendor\": \"n/a\", \"product\": \"n/a\", \"versions\": [{\"status\": \"affected\", \"version\": \"n/a\"}]}], \"references\": [{\"url\": \"https://github.com/PinkDraconian/PoC-Langchain-RCE/blob/main/README.md\"}, {\"url\": \"https://github.com/langchain-ai/langchain/blob/f96dd57501131840b713ed7c2e86cbf1ddc2761f/libs/core/langchain_core/utils/loading.py\"}, {\"url\": \"https://github.com/langchain-ai/langchain/pull/18600\"}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a load_chain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub repository. The outcome can be disclosure of an API key for a large language model online service, or remote code execution. (A patch is available as of release 0.1.29 of langchain-core.)\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"text\", \"description\": \"n/a\"}]}], \"providerMetadata\": {\"orgId\": \"8254265b-2729-46b6-b9e3-3dfca2d5bfca\", \"shortName\": \"mitre\", \"dateUpdated\": \"2024-03-13T21:00:45.400995\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2024-28088\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2024-08-26T19:44:45.330Z\", \"dateReserved\": \"2024-03-03T00:00:00\", \"assignerOrgId\": \"8254265b-2729-46b6-b9e3-3dfca2d5bfca\", \"datePublished\": \"2024-03-03T00:00:00\", \"assignerShortName\": \"mitre\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.1"
    }
  }
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Sightings

Author Source Type Date

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or seen somewhere by the user.
  • Confirmed: The vulnerability is confirmed from an analyst perspective.
  • Exploited: This vulnerability was exploited and seen by the user reporting the sighting.
  • Patched: This vulnerability was successfully patched by the user reporting the sighting.
  • Not exploited: This vulnerability was not exploited or seen by the user reporting the sighting.
  • Not confirmed: The user expresses doubt about the veracity of the vulnerability.
  • Not patched: This vulnerability was not successfully patched by the user reporting the sighting.