cve/2023/CVE-2023-29374.md

### [CVE-2023-29374](https://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2023-29374)
![](https://img.shields.io/static/v1?label=Product&message=n%2Fa&color=blue)
![](https://img.shields.io/static/v1?label=Version&message=n%2Fa&color=blue)
![](https://img.shields.io/static/v1?label=Vulnerability&message=n%2Fa&color=brighgreen)

### Description

In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method.

### POC

#### Reference
- https://github.com/hwchase17/langchain/issues/1026

#### Github
- https://github.com/cckuailong/awesome-gpt-security
- https://github.com/corca-ai/awesome-llm-security
- https://github.com/invariantlabs-ai/invariant
- https://github.com/zgimszhd61/llm-security-quickstart