CVE-2023-32786

Published Oct 20, 2023

Last updated a year ago

Overview

Description: In Langchain through 0.0.155, prompt injection allows an attacker to force the service to retrieve data from an arbitrary URL, essentially providing SSRF and potentially injecting content into downstream tasks.
Source: cve@mitre.org
NVD status: Analyzed

Risk scores

CVSS 3.1

Type: Primary
Base score: 7.5
Impact score: 3.6
Exploitability score: 3.9
Vector string: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Severity: HIGH

Weaknesses

nvd@nist.gov: CWE-74

Hype score: Not currently trending

Configurations

[
  {
    "nodes": [
      {
        "negate": false,
        "cpeMatch": [
          {
            "criteria": "cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*",
            "vulnerable": true,
            "matchCriteriaId": "02E32772-8A62-461E-A121-F894FD16B540",
            "versionEndIncluding": "0.0.155"
          }
        ],
        "operator": "OR"
      }
    ]
  }
]

References