CVE-2024-1455 (GCVE-0-2024-1455)

Vulnerability from cvelistv5 – Published: 2024-03-26 14:03 – Updated: 2024-08-15 15:56
VLAI?
Summary
A vulnerability in the langchain-ai/langchain repository allows for a Billion Laughs Attack, a type of XML External Entity (XXE) exploitation. By nesting multiple layers of entities within an XML document, an attacker can cause the XML parser to consume excessive CPU and memory resources, leading to a denial of service (DoS).
Severity ?
5.9 (Medium)
CVSS:3.0/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H
CWE
  • CWE-776 - Improper Restriction of Recursive Entity References in DTDs
Assigner
References
Impacted products
Vendor Product Version
langchain-ai langchain-ai/langchain Affected: unspecified , < 0.1.35 (custom)
Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "providerMetadata": {
          "dateUpdated": "2024-08-01T18:40:21.288Z",
          "orgId": "af854a3a-2127-422b-91ae-364da2661108",
          "shortName": "CVE"
        },
        "references": [
          {
            "tags": [
              "x_transferred"
            ],
            "url": "https://huntr.com/bounties/4353571f-c70d-4bfd-ac08-3a89cecb45b6"
          },
          {
            "tags": [
              "x_transferred"
            ],
            "url": "https://github.com/langchain-ai/langchain/commit/727d5023ce88e18e3074ef620a98137d26ff92a3"
          }
        ],
        "title": "CVE Program Container"
      },
      {
        "affected": [
          {
            "cpes": [
              "cpe:2.3:a:langchain-ai:langchain-ai\\/langchain:*:*:*:*:*:*:*:*"
            ],
            "defaultStatus": "unknown",
            "product": "langchain-ai\\/langchain",
            "vendor": "langchain-ai",
            "versions": [
              {
                "lessThan": "0.1.35",
                "status": "affected",
                "version": "0",
                "versionType": "custom"
              }
            ]
          }
        ],
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2024-1455",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2024-08-15T15:55:06.717038Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2024-08-15T15:56:19.154Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "langchain-ai/langchain",
          "vendor": "langchain-ai",
          "versions": [
            {
              "lessThan": "0.1.35",
              "status": "affected",
              "version": "unspecified",
              "versionType": "custom"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "A vulnerability in the langchain-ai/langchain repository allows for a Billion Laughs Attack, a type of XML External Entity (XXE) exploitation. By nesting multiple layers of entities within an XML document, an attacker can cause the XML parser to consume excessive CPU and memory resources, leading to a denial of service (DoS). "
        }
      ],
      "metrics": [
        {
          "cvssV3_0": {
            "attackComplexity": "HIGH",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 5.9,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "NONE",
            "integrityImpact": "NONE",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.0/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H",
            "version": "3.0"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-776",
              "description": "CWE-776 Improper Restriction of Recursive Entity References in DTDs",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2024-04-16T11:10:22.131Z",
        "orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
        "shortName": "@huntr_ai"
      },
      "references": [
        {
          "url": "https://huntr.com/bounties/4353571f-c70d-4bfd-ac08-3a89cecb45b6"
        },
        {
          "url": "https://github.com/langchain-ai/langchain/commit/727d5023ce88e18e3074ef620a98137d26ff92a3"
        }
      ],
      "source": {
        "advisory": "4353571f-c70d-4bfd-ac08-3a89cecb45b6",
        "discovery": "EXTERNAL"
      },
      "title": "Billion Laughs Attack leading to DoS in langchain-ai/langchain"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
    "assignerShortName": "@huntr_ai",
    "cveId": "CVE-2024-1455",
    "datePublished": "2024-03-26T14:03:46.647Z",
    "dateReserved": "2024-02-12T16:51:50.188Z",
    "dateUpdated": "2024-08-15T15:56:19.154Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1",
  "vulnerability-lookup:meta": {
    "fkie_nvd": {
      "descriptions": "[{\"lang\": \"en\", \"value\": \"A vulnerability in the langchain-ai/langchain repository allows for a Billion Laughs Attack, a type of XML External Entity (XXE) exploitation. By nesting multiple layers of entities within an XML document, an attacker can cause the XML parser to consume excessive CPU and memory resources, leading to a denial of service (DoS). \"}, {\"lang\": \"es\", \"value\": \"XMLOutputParser en LangChain utiliza el m\\u00f3dulo etree del analizador XML en la biblioteca est\\u00e1ndar de Python que tiene algunas vulnerabilidades XML; consulte: https://docs.python.org/3/library/xml.html Esto afecta principalmente a los usuarios que combinan un LLM (o agente) con `XMLOutputParser` y exponen el componente a trav\\u00e9s de un endpoint en un servicio web. Esto permitir\\u00eda que una parte malintencionada intentara manipular el LLM para producir un payload malicioso para el analizador que comprometer\\u00eda la disponibilidad del servicio. Un ataque exitoso se basa en: 1. Uso de XMLOutputParser 2. Pasar entradas maliciosas al XMLOutputParser, ya sea directamente o intentando manipular un LLM para que lo haga en nombre del usuario 3. Exponer el componente a trav\\u00e9s de un servicio web\"}]",
      "id": "CVE-2024-1455",
      "lastModified": "2024-11-21T08:50:37.310",
      "metrics": "{\"cvssMetricV30\": [{\"source\": \"security@huntr.dev\", \"type\": \"Secondary\", \"cvssData\": {\"version\": \"3.0\", \"vectorString\": \"CVSS:3.0/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H\", \"baseScore\": 5.9, \"baseSeverity\": \"MEDIUM\", \"attackVector\": \"NETWORK\", \"attackComplexity\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"userInteraction\": \"NONE\", \"scope\": \"UNCHANGED\", \"confidentialityImpact\": \"NONE\", \"integrityImpact\": \"NONE\", \"availabilityImpact\": \"HIGH\"}, \"exploitabilityScore\": 2.2, \"impactScore\": 3.6}]}",
      "published": "2024-03-26T14:15:08.450",
      "references": "[{\"url\": \"https://github.com/langchain-ai/langchain/commit/727d5023ce88e18e3074ef620a98137d26ff92a3\", \"source\": \"security@huntr.dev\"}, {\"url\": \"https://huntr.com/bounties/4353571f-c70d-4bfd-ac08-3a89cecb45b6\", \"source\": \"security@huntr.dev\"}, {\"url\": \"https://github.com/langchain-ai/langchain/commit/727d5023ce88e18e3074ef620a98137d26ff92a3\", \"source\": \"af854a3a-2127-422b-91ae-364da2661108\"}, {\"url\": \"https://huntr.com/bounties/4353571f-c70d-4bfd-ac08-3a89cecb45b6\", \"source\": \"af854a3a-2127-422b-91ae-364da2661108\"}]",
      "sourceIdentifier": "security@huntr.dev",
      "vulnStatus": "Awaiting Analysis",
      "weaknesses": "[{\"source\": \"security@huntr.dev\", \"type\": \"Secondary\", \"description\": [{\"lang\": \"en\", \"value\": \"CWE-776\"}]}]"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2024-1455\",\"sourceIdentifier\":\"security@huntr.dev\",\"published\":\"2024-03-26T14:15:08.450\",\"lastModified\":\"2025-07-30T20:06:23.577\",\"vulnStatus\":\"Analyzed\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"A vulnerability in the langchain-ai/langchain repository allows for a Billion Laughs Attack, a type of XML External Entity (XXE) exploitation. By nesting multiple layers of entities within an XML document, an attacker can cause the XML parser to consume excessive CPU and memory resources, leading to a denial of service (DoS). \"},{\"lang\":\"es\",\"value\":\"XMLOutputParser en LangChain utiliza el m\u00f3dulo etree del analizador XML en la biblioteca est\u00e1ndar de Python que tiene algunas vulnerabilidades XML; consulte: https://docs.python.org/3/library/xml.html Esto afecta principalmente a los usuarios que combinan un LLM (o agente) con `XMLOutputParser` y exponen el componente a trav\u00e9s de un endpoint en un servicio web. Esto permitir\u00eda que una parte malintencionada intentara manipular el LLM para producir un payload malicioso para el analizador que comprometer\u00eda la disponibilidad del servicio. Un ataque exitoso se basa en: 1. Uso de XMLOutputParser 2. Pasar entradas maliciosas al XMLOutputParser, ya sea directamente o intentando manipular un LLM para que lo haga en nombre del usuario 3. Exponer el componente a trav\u00e9s de un servicio web\"}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"nvd@nist.gov\",\"type\":\"Primary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H\",\"baseScore\":5.9,\"baseSeverity\":\"MEDIUM\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"HIGH\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"NONE\",\"integrityImpact\":\"NONE\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":2.2,\"impactScore\":3.6}],\"cvssMetricV30\":[{\"source\":\"security@huntr.dev\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.0\",\"vectorString\":\"CVSS:3.0/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H\",\"baseScore\":5.9,\"baseSeverity\":\"MEDIUM\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"HIGH\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"NONE\",\"integrityImpact\":\"NONE\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":2.2,\"impactScore\":3.6}]},\"weaknesses\":[{\"source\":\"security@huntr.dev\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-776\"}]}],\"configurations\":[{\"nodes\":[{\"operator\":\"OR\",\"negate\":false,\"cpeMatch\":[{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*\",\"versionStartIncluding\":\"0.1.4\",\"versionEndIncluding\":\"0.1.35\",\"matchCriteriaId\":\"E2048421-A31F-490C-B3B5-EA3C4033A4E7\"}]}]}],\"references\":[{\"url\":\"https://github.com/langchain-ai/langchain/commit/727d5023ce88e18e3074ef620a98137d26ff92a3\",\"source\":\"security@huntr.dev\",\"tags\":[\"Patch\"]},{\"url\":\"https://huntr.com/bounties/4353571f-c70d-4bfd-ac08-3a89cecb45b6\",\"source\":\"security@huntr.dev\",\"tags\":[\"Exploit\",\"Third Party Advisory\"]},{\"url\":\"https://github.com/langchain-ai/langchain/commit/727d5023ce88e18e3074ef620a98137d26ff92a3\",\"source\":\"af854a3a-2127-422b-91ae-364da2661108\",\"tags\":[\"Patch\"]},{\"url\":\"https://huntr.com/bounties/4353571f-c70d-4bfd-ac08-3a89cecb45b6\",\"source\":\"af854a3a-2127-422b-91ae-364da2661108\",\"tags\":[\"Exploit\",\"Third Party Advisory\"]}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CVE Program Container\", \"references\": [{\"url\": \"https://huntr.com/bounties/4353571f-c70d-4bfd-ac08-3a89cecb45b6\", \"tags\": [\"x_transferred\"]}, {\"url\": \"https://github.com/langchain-ai/langchain/commit/727d5023ce88e18e3074ef620a98137d26ff92a3\", \"tags\": [\"x_transferred\"]}], \"providerMetadata\": {\"orgId\": \"af854a3a-2127-422b-91ae-364da2661108\", \"shortName\": \"CVE\", \"dateUpdated\": \"2024-08-01T18:40:21.288Z\"}}, {\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2024-1455\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2024-08-15T15:55:06.717038Z\"}}}], \"affected\": [{\"cpes\": [\"cpe:2.3:a:langchain-ai:langchain-ai\\\\/langchain:*:*:*:*:*:*:*:*\"], \"vendor\": \"langchain-ai\", \"product\": \"langchain-ai\\\\/langchain\", \"versions\": [{\"status\": \"affected\", \"version\": \"0\", \"lessThan\": \"0.1.35\", \"versionType\": \"custom\"}], \"defaultStatus\": \"unknown\"}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2024-08-15T15:56:13.148Z\"}}], \"cna\": {\"title\": \"Billion Laughs Attack leading to DoS in langchain-ai/langchain\", \"source\": {\"advisory\": \"4353571f-c70d-4bfd-ac08-3a89cecb45b6\", \"discovery\": \"EXTERNAL\"}, \"metrics\": [{\"cvssV3_0\": {\"scope\": \"UNCHANGED\", \"version\": \"3.0\", \"baseScore\": 5.9, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"MEDIUM\", \"vectorString\": \"CVSS:3.0/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H\", \"integrityImpact\": \"NONE\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"HIGH\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"NONE\"}}], \"affected\": [{\"vendor\": \"langchain-ai\", \"product\": \"langchain-ai/langchain\", \"versions\": [{\"status\": \"affected\", \"version\": \"unspecified\", \"lessThan\": \"0.1.35\", \"versionType\": \"custom\"}]}], \"references\": [{\"url\": \"https://huntr.com/bounties/4353571f-c70d-4bfd-ac08-3a89cecb45b6\"}, {\"url\": \"https://github.com/langchain-ai/langchain/commit/727d5023ce88e18e3074ef620a98137d26ff92a3\"}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"A vulnerability in the langchain-ai/langchain repository allows for a Billion Laughs Attack, a type of XML External Entity (XXE) exploitation. By nesting multiple layers of entities within an XML document, an attacker can cause the XML parser to consume excessive CPU and memory resources, leading to a denial of service (DoS). \"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-776\", \"description\": \"CWE-776 Improper Restriction of Recursive Entity References in DTDs\"}]}], \"providerMetadata\": {\"orgId\": \"c09c270a-b464-47c1-9133-acb35b22c19a\", \"shortName\": \"@huntr_ai\", \"dateUpdated\": \"2024-04-16T11:10:22.131Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2024-1455\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2024-08-15T15:56:19.154Z\", \"dateReserved\": \"2024-02-12T16:51:50.188Z\", \"assignerOrgId\": \"c09c270a-b464-47c1-9133-acb35b22c19a\", \"datePublished\": \"2024-03-26T14:03:46.647Z\", \"assignerShortName\": \"@huntr_ai\"}",
      "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 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.