CVE-2023-32786
High
Description
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.
SeverityHigh
CVSS7.5
Exploit probability—
ProductLangchain
PublishedOct 20, 2023
First seenOct 20, 2023
How to fix
Update
- langchain0.0.329 or later
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| langchain langchain | v ≤ 0.0.155 | — |
| langchainPyPI | v < 0.0.329 | 0.0.329 |
Check your version
Choose the product and enter the version you run to see whether it falls in the affected range.
In the Intelligence 360 plan
Attack Surface Management
See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.