Skip to main content

Improper Control of Generation of Code ('Code Injection')

CVE-2024-5826

High
9.8/10

Summary

In the package vanna versions 0.0.22 and after, the "vanna.ask" function is vulnerable to Remote Code Execution (RCE) 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 (RCE) on the app backend server, potentially gaining full control of the server.

  • LOW
  • NETWORK
  • HIGH
  • UNCHANGED
  • NONE
  • NONE
  • HIGH
  • HIGH

CWE-94 - Code Injection

Code injection is a type of vulnerability that allows an attacker to execute arbitrary code. This vulnerability fully compromises the machine and can cause a wide variety of security issues, such as unauthorized access to sensitive information, manipulation of data, denial of service attacks etc. Code injection is different from command injection in the fact that it is limited by the functionality of the injected language (e.g. PHP), as opposed to command injection, which leverages existing code to execute commands, usually within the context of a shell.

References

Advisory Timeline

  • Published