VYPR
← All advisories
High severity8.8NVD Advisory· Published Mar 20, 2025· Updated Jun 17, 2026

CVE-2024-10950

CVE-2024-10950

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.

AI Insight

LLM-synthesized narrative grounded in this CVE's description and references.

Affected products

3
  • Binary Husky/Gpt Academic2 versions
    cpe:2.3:a:binary-husky:gpt_academic:*:*:*:*:*:*:*:*+ 1 more
    • cpe:2.3:a:binary-husky:gpt_academic:*:*:*:*:*:*:*:*range: <=3.83
    • (no CPE)range: <=3.83
  • binary-husky/binary-husky/gpt_academicv5
    Range: unspecified

Patches

Vulnerability mechanics

References

1

News mentions

0

No linked articles in our index yet.