Langchain through 0.0.155: Prompt Injection Vulnerability

CVE-2023-32786 · HIGH Severity

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

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.

Learn more about our Web Application Penetration Testing UK.