cve/2024/CVE-2024-6331.md

### [CVE-2024-6331](https://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2024-6331)
![](https://img.shields.io/static/v1?label=Product&message=stitionai%2Fdevika&color=blue)
![](https://img.shields.io/static/v1?label=Version&message=unspecified%3C%3D%20latest%20&color=brighgreen)
![](https://img.shields.io/static/v1?label=Vulnerability&message=CWE-74%20Improper%20Neutralization%20of%20Special%20Elements%20in%20Output%20Used%20by%20a%20Downstream%20Component%20('Injection')&color=brighgreen)

### Description

stitionai/devika main branch as of commit cdfb782b0e634b773b10963c8034dc9207ba1f9f is vulnerable to Local File Read (LFI) by Prompt Injection. The integration of Google Gimini 1.0 Pro with `HarmBlockThreshold.BLOCK_NONE` for `HarmCategory.HARM_CATEGORY_HATE_SPEECH` and `HarmCategory.HARM_CATEGORY_HARASSMENT` in `safety_settings` disables content protection. This allows malicious commands to be executed, such as reading sensitive file contents like `/etc/passwd`.

### POC

#### Reference
No PoCs from references.

#### Github
- https://github.com/fkie-cad/nvd-json-data-feeds