CVE-2024-10950

Affects: prompt injection

CVSS: HIGH · 8.8v3.0
CVSS:3.0/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Published: 2025-03-20
Weakness: CWE-94
Source: nvd.nist.gov/vuln/detail/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.

References

https://huntr.com/bounties/9abb1617-0c1d-42c7-a647-d9d2b39c6866

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2024-10950 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.

AI Red-Teaming course →·Browse MITRE ATLAS techniques

Related AI/LLM CVEs

AI security training, taught by people who do the work.

Hands-on courses on adversarial AI, prompt injection, and ML pipeline security.

Explore AI Red-Teaming