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.
References
| Link | Resource |
|---|---|
| https://gist.github.com/rharang/d265f46fc3161b31ac2e81db44d662e1 | Third Party Advisory |
| https://gist.github.com/rharang/d265f46fc3161b31ac2e81db44d662e1 | Third Party Advisory |
Configurations
History
No history.
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')
