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.
Injection
ProviderTypeBase ScoreAtk. VectorAtk. ComplexityPriv. RequiredVector
NISTNIST
7.5 HIGH
NETWORK
LOW
NONE
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
mitreCNA
---
---
CVEADP
---
---
CISA-ADPADP
---
---
Base Score
CVSS 3.x
EPSS Score
Percentile: 33%
VendorProductVersion
langchainlangchain
𝑥
≤ 0.0.155
𝑥
= Vulnerable software versions
Common Weakness Enumeration
References
https://gist.github.com/rharang/d265f46fc3161b31ac2e81db44d662e1
https://gist.github.com/rharang/d265f46fc3161b31ac2e81db44d662e1