github - ghsa-fprp-p869-w6q2

GHSA-FPRP-P869-W6Q2

Vulnerability from github – Published: 2023-04-05 03:30 – Updated: 2025-02-12 18:33

Summary

LangChain vulnerable to code injection

Details

In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec() method.

Severity ?

9.8 (Critical)


                  
                    CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

9.3 (Critical)


                  
                    CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "langchain"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "last_affected": "0.0.131"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2023-29374"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-74",
      "CWE-94"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2023-04-05T19:39:41Z",
    "nvd_published_at": "2023-04-05T02:15:00Z",
    "severity": "CRITICAL"
  },
  "details": "In LangChain through 0.0.131, the `LLMMathChain` chain allows prompt injection attacks that can execute arbitrary code via the Python `exec()` method.",
  "id": "GHSA-fprp-p869-w6q2",
  "modified": "2025-02-12T18:33:26Z",
  "published": "2023-04-05T03:30:17Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2023-29374"
    },
    {
      "type": "WEB",
      "url": "https://github.com/hwchase17/langchain/issues/1026"
    },
    {
      "type": "WEB",
      "url": "https://github.com/hwchase17/langchain/issues/814"
    },
    {
      "type": "WEB",
      "url": "https://github.com/hwchase17/langchain/pull/1119"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/langchain-ai/langchain"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pypa/advisory-database/tree/main/vulns/langchain/PYSEC-2023-18.yaml"
    },
    {
      "type": "WEB",
      "url": "https://twitter.com/rharang/status/1641899743608463365/photo/1"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
      "type": "CVSS_V4"
    }
  ],
  "summary": "LangChain vulnerable to code injection"
}

CVE-2023-29374 (GCVE-0-2023-29374)

Vulnerability from cvelistv5 – Published: 2023-04-05 00:00 – Updated: 2025-02-12 16:24

Summary

In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method.

Severity ?

9.8 (Critical)


                        
                          CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

CWE

Assigner

mitre

References

URL

Tags

	https://github.com/hwchase17/langchain/pull/1119
	https://github.com/hwchase17/langchain/issues/814
	https://twitter.com/rharang/status/16418997436084…
	https://github.com/hwchase17/langchain/issues/1026

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "providerMetadata": {
          "dateUpdated": "2024-08-02T14:07:45.736Z",
          "orgId": "af854a3a-2127-422b-91ae-364da2661108",
          "shortName": "CVE"
        },
        "references": [
          {
            "tags": [
              "x_transferred"
            ],
            "url": "https://github.com/hwchase17/langchain/pull/1119"
          },
          {
            "tags": [
              "x_transferred"
            ],
            "url": "https://github.com/hwchase17/langchain/issues/814"
          },
          {
            "tags": [
              "x_transferred"
            ],
            "url": "https://twitter.com/rharang/status/1641899743608463365/photo/1"
          },
          {
            "tags": [
              "x_transferred"
            ],
            "url": "https://github.com/hwchase17/langchain/issues/1026"
          }
        ],
        "title": "CVE Program Container"
      },
      {
        "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"
            }
          },
          {
            "other": {
              "content": {
                "id": "CVE-2023-29374",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2025-02-12T16:14:23.167174Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "problemTypes": [
          {
            "descriptions": [
              {
                "cweId": "CWE-74",
                "description": "CWE-74 Improper Neutralization of Special Elements in Output Used by a Downstream Component (\u0027Injection\u0027)",
                "lang": "en",
                "type": "CWE"
              }
            ]
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2025-02-12T16:24:39.291Z",
          "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": "In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method."
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "description": "n/a",
              "lang": "en",
              "type": "text"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2023-04-05T00:00:00.000Z",
        "orgId": "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
        "shortName": "mitre"
      },
      "references": [
        {
          "url": "https://github.com/hwchase17/langchain/pull/1119"
        },
        {
          "url": "https://github.com/hwchase17/langchain/issues/814"
        },
        {
          "url": "https://twitter.com/rharang/status/1641899743608463365/photo/1"
        },
        {
          "url": "https://github.com/hwchase17/langchain/issues/1026"
        }
      ]
    }
  },
  "cveMetadata": {
    "assignerOrgId": "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
    "assignerShortName": "mitre",
    "cveId": "CVE-2023-29374",
    "datePublished": "2023-04-05T00:00:00.000Z",
    "dateReserved": "2023-04-05T00:00:00.000Z",
    "dateUpdated": "2025-02-12T16:24:39.291Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1"
}

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.

Action not permitted

GHSA-FPRP-P869-W6Q2

CVE-2023-29374 (GCVE-0-2023-29374)

Tags

Sightings

Nomenclature