CVE-2024-5826

June 27, 2024, 7:25 p.m.

CVSS Score

9.8 / 10

Product(s) Impacted

vanna-ai/vanna

  • latest version

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.

Weaknesses

CWE-94
Improper Control of Generation of Code ('Code Injection')

The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment.

CWE ID: 94

Date

Published: June 27, 2024, 7:15 p.m.

Last Modified: June 27, 2024, 7:25 p.m.

Status : Awaiting Analysis

CVE has been marked for Analysis. Normally once in this state the CVE will be analyzed by NVD staff within 24 hours.

More info

Source

security@huntr.dev

CVSS Data

Attack Vector

NETWORK

Attack Complexity

LOW

Privileges Required

NONE

Scope

UNCHANGED

Confidentiality Impact

HIGH

Integrity Impact

HIGH

Availability Impact

HIGH

Base Score
9.8
Exploitability Score
3.9
Impact Score
5.9
Base Severity
CRITICAL
CVSS Vector String

The CVSS vector string provides an in-depth view of the vulnerability metrics.

View Vector String

CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References