CVE-2023-32786

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.
Configurations

Configuration 1 (hide)

cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*

History

21 Nov 2024, 08:04

Type Values Removed Values Added
References () https://gist.github.com/rharang/d265f46fc3161b31ac2e81db44d662e1 - Third Party Advisory () https://gist.github.com/rharang/d265f46fc3161b31ac2e81db44d662e1 - Third Party Advisory

27 Oct 2023, 21:44

Type Values Removed Values Added
References (MISC) https://gist.github.com/rharang/d265f46fc3161b31ac2e81db44d662e1 - (MISC) https://gist.github.com/rharang/d265f46fc3161b31ac2e81db44d662e1 - Third Party Advisory
CVSS v2 : unknown
v3 : unknown
v2 : unknown
v3 : 7.5
CWE CWE-74
First Time Langchain langchain
Langchain
CPE cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*

20 Oct 2023, 22:15

Type Values Removed Values Added
New CVE

Information

Published : 2023-10-20 22:15

Updated : 2024-11-21 08:04


NVD link : CVE-2023-32786

Mitre link : CVE-2023-32786

CVE.ORG link : CVE-2023-32786


JSON object : View

Products Affected

langchain

  • langchain
CWE
CWE-74

Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')