) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.
Search Results (Refine Search)
- Results Type: Overview
- Keyword (text search): cpe:2.3:a:langchain:langchain:0.0.1:rc3:*:*:*:*:*:*
- CPE Name Search: true
| Vuln ID | Summary | CVSS Severity |
|---|---|---|
| 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. Published: October 20, 2023; 6:15:10 PM -0400 |
V4.0:(not available) V3.1: 7.5 HIGH V2.0:(not available) |
| CVE-2023-46229 |
LangChain before 0.0.317 allows SSRF via document_loaders/recursive_url_loader.py because crawling can proceed from an external server to an internal server. Published: October 19, 2023; 1:15:58 AM -0400 |
V4.0:(not available) V3.1: 8.8 HIGH V2.0:(not available) |
| CVE-2023-39659 |
An issue in langchain langchain-ai v.0.0.232 and before allows a remote attacker to execute arbitrary code via a crafted script to the PythonAstREPLTool._run component. Published: August 15, 2023; 1:15:12 PM -0400 |
V4.0:(not available) V3.1: 9.8 CRITICAL V2.0:(not available) |
| CVE-2023-38896 |
An issue in Harrison Chase langchain v.0.0.194 and before allows a remote attacker to execute arbitrary code via the from_math_prompt and from_colored_object_prompt functions. Published: August 15, 2023; 1:15:12 PM -0400 |
V4.0:(not available) V3.1: 9.8 CRITICAL V2.0:(not available) |
| CVE-2023-29374 |
In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method. Published: April 04, 2023; 10:15:37 PM -0400 |
V4.0:(not available) V3.1: 9.8 CRITICAL V2.0:(not available) |