Home » Database

AVID-2026-R0017

Description

Code Injection in binary-husky/gpt_academic (CVE-2024-10950)

Details

In binary-husky/gpt_academic version <= 3.83, the plugin CodeInterpreter is vulnerable to code injection caused by prompt injection. The root cause is the execution of user-provided prompts that generate untrusted code without a sandbox, allowing the execution of parts of the LLM-generated code. This vulnerability can be exploited by an attacker to achieve remote code execution (RCE) on the application backend server, potentially gaining full control of the server.

References

Affected or Relevant Artifacts

  • Developer: binary-husky
  • Deployer: binary-husky
  • Artifact Details:
TypeName
Systembinary-husky/gpt_academic

Impact

AVID Taxonomy Categorization

  • Risk domains: Security
  • SEP subcategories: S0100: Software Vulnerability
  • Lifecycle stages: L06: Deployment

CVSS

Version3.0
Vector StringCVSS:3.0/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Base Score8.8
Base Severity🔴 High
Attack VectorNETWORK
Attack Complexity🟢 Low
Privileges Required🟢 Low
User InteractionNONE
ScopeUNCHANGED
Confidentiality Impact🔴 High
Integrity Impact🔴 High
Availability Impact🔴 High

CWE

IDDescription
CWE-94CWE-94 Improper Control of Generation of Code

Other information

  • Report Type: Advisory
  • Credits:
  • Date Reported: 2025-03-20
  • Version: 0.3.1
  • AVID Entry