Skip to content

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

HighCVSS 8.8 EPSS 1.5%
Published
Updated
Exploit status
No public exploit known
CISA SSVC
Proof of concept public · automatable: no · technical impact: total

Description

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.

Upgrade path

2 packages: 2 fixed.

PackageAffectedFixed inStatus
binary-husky gpt_academic <= 3.83 after 3.83 Fixed
binary-husky/gpt_academic <= latest after latest Fixed

Affected products

ProductAffected versionsFixed in
binary-husky/gpt_academic <= latest No fix listed
binary-husky gpt_academic <= 3.83 No fix listed

References