CVE-2024-5826

Remote Code Execution via Prompt Injection in vanna-ai/vanna

Published Jun 27, 2024 CVSS 3.0 · 9.8 Critical EPSS < 1% KEV · Not listed
Description
In the latest version of vanna-ai/vanna, the `vanna.ask` function is vulnerable to remote code execution due to prompt injection. The root cause is the lack of a sandbox when executing LLM-generated code, allowing an attacker to manipulate the code executed by the `exec` function in `src/vanna/base/base.py`. This vulnerability can be exploited by an attacker to achieve remote code execution on the app backend server, potentially gaining full control of the server.

Remediation

No solution or workaround provided in the CVE record

Tracking

Sign in to view the affected projects.

Advisories

Source ID Title
EUVD EUVD EUVD-2024-2162 In the latest version of vanna-ai/vanna, the `vanna.ask` function is vulnerable to remote code execution due to prompt injection. The root cause is the lack of a sandbox when executing LLM-generated code, allowing an attacker to manipulate the code executed by the `exec` function in `src/vanna/base/base.py`. This vulnerability can be exploited by an attacker to achieve remote code execution on the app backend server, potentially gaining full control of the server.
Github GHSA Github GHSA GHSA-rrqq-fv6m-692m vanna vulnerable to remote code execution caused by prompt injection
History

No history.

Weaknesses

Sources

Status
PUBLISHED
Assigner
@huntr_ai
Published
Updated
Oct 15, 2025, 12:50 PM
Reserved
Jun 10, 2024, 10:43 PM
Status
Deferred
Published
Jun 27, 2024, 7:15 PM
Modified
Jun 17, 2026, 8:16 AM