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

High 7.5 Published 4 Aug 2024 Updated 30 Aug 2024

Attackers can read sensitive files via prompt injection due to disabled safety settings in the Devika AI agent framework.

Exploited in the wild: Not known
Login needed: Not needed
Attackable: Over the internet
Victim action needed: Not needed
Fix: None listed

What is CVE-2024-6331?

CVE-2024-6331 is a high-severity code injection vulnerability in stitionai/devika, published on 4 Aug 2024. An attacker can exploit it over the internet without logging in, with no action from the victim.

Official 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`.

Weakness: CWE-74

Which versions are affected by CVE-2024-6331?

It affects 1 product.

Products include Stitionai Devika.

How do I fix CVE-2024-6331?

No fix has been published for CVE-2024-6331 yet. Limit exposure of the affected software until one is available.

Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.

Is CVE-2024-6331 being exploited?

It is not confirmed as exploited in the wild, but public exploit code for CVE-2024-6331 exists.

Sources

Also known as GHSA-699f-m7wm-gv75.