LIVE NEWSROOM · --:-- · May 25, 2026
A LIBRARY FOR SECURITY RESEARCHERS

CVE DATABASE  /  CVE-2023-32786

CVE-2023-32786

CVSS 7.5 · HIGH

Summary

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.

CVSS 3.1 breakdown

Base score7.5 (HIGH)
VectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Attack vectorNETWORK
Attack complexityLOW
Privileges requiredNONE
User interactionNONE
ScopeUNCHANGED
ConfidentialityHIGH
IntegrityNONE
AvailabilityNONE

Weakness type (CWE)

Affected products

Langchain langchain
Check this CVE live

Use our free CVE Lookup tool for the latest NVD record, or browse the full CISA KEV catalog.

References

Data: NIST NVD. NVD last modified 2024-11-21. Always verify against the vendor advisory before acting.

Scroll to Top