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.
Exploitability
AV:NAC:LPR:NUI:NScope
S:UImpact
C:HI:NA:N7.5/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N