GHSA-Q84M-RMW3-4382

Vulnerability from github – Published: 2024-03-26 15:30 – Updated: 2024-03-27 17:46
VLAI?
Summary
LangChain's XMLOutputParser vulnerable to XML Entity Expansion
Details

The XMLOutputParser in LangChain uses the etree module from the XML parser in the standard python library which has some XML vulnerabilities; see: https://docs.python.org/3/library/xml.html

This primarily affects users that combine an LLM (or agent) with the XMLOutputParser and expose the component via an endpoint on a web-service.

This would allow a malicious party to attempt to manipulate the LLM to produce a malicious payload for the parser that would compromise the availability of the service.

A successful attack is predicated on:

  1. Usage of XMLOutputParser
  2. Passing of malicious input into the XMLOutputParser either directly or by trying to manipulate an LLM to do so on the users behalf
  3. Exposing the component via a web-service
Severity ?
5.9 (Medium)
CVSS:3.0/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "langchain-core"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.1.35"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2024-1455"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-776"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2024-03-26T21:22:28Z",
    "nvd_published_at": "2024-03-26T14:15:08Z",
    "severity": "MODERATE"
  },
  "details": "The XMLOutputParser in LangChain uses the etree module from the XML parser in the standard python library which has some XML vulnerabilities; see: https://docs.python.org/3/library/xml.html\n\nThis primarily affects users that combine an LLM (or agent) with the `XMLOutputParser` and expose the component via an endpoint on a web-service. \n\nThis would allow a malicious party to attempt to manipulate the LLM to produce a malicious payload for the parser that would compromise the availability of the service.\n\nA successful attack is predicated on:\n\n1. Usage of XMLOutputParser\n2. Passing of malicious input into the XMLOutputParser either directly or by trying to manipulate an LLM to do so on the users behalf\n3. Exposing the component via a web-service",
  "id": "GHSA-q84m-rmw3-4382",
  "modified": "2024-03-27T17:46:43Z",
  "published": "2024-03-26T15:30:50Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2024-1455"
    },
    {
      "type": "WEB",
      "url": "https://github.com/langchain-ai/langchain/pull/17250"
    },
    {
      "type": "WEB",
      "url": "https://github.com/langchain-ai/langchain/pull/19653"
    },
    {
      "type": "WEB",
      "url": "https://github.com/langchain-ai/langchain/pull/19660"
    },
    {
      "type": "WEB",
      "url": "https://github.com/langchain-ai/langchain/commit/727d5023ce88e18e3074ef620a98137d26ff92a3"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/langchain-ai/langchain"
    },
    {
      "type": "WEB",
      "url": "https://huntr.com/bounties/4353571f-c70d-4bfd-ac08-3a89cecb45b6"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.0/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "LangChain\u0027s XMLOutputParser vulnerable to XML Entity Expansion"
}


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.