CVE-2024-6331 HIGH

CVE-2024-6331: Injection by Prompt Injection in stitionai/devika

Vendor Stitionai
Product stitionai/devika
Weakness CWE-74
Published August 4, 2024
Last update August 30, 2024
View on NVD All CVEs

CVSS base score

7.5/10
Attack vector Network
Attack complexity Low
Privileges required None
User interaction None
Confidentiality High
Integrity None

CVSS vector

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

What the vulnerability does

01Description

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`.

Key dates

02Disclosure timeline

August 4, 2024 CVE published
August 30, 2024 Record updated