CVE 6.9 MEDIUM

FoundationAgents MetaGPT HumanEvalBenchmark/MBPPBenchmark check_solution code injection_CVE-2026-5970

6.9 / 10
MEDIUM
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P

Description

A vulnerability was detected in FoundationAgents MetaGPT up to 0.8.1. This affects the function check_solution of the component HumanEvalBenchmark/MBPPBenchmark. Performing a manipulation results in code injection. The attack may be initiated remotely. The exploit is now public and may be used. The project was informed of the problem early through a pull request but has not reacted yet.

Basic Information

ID CVE-2026-5970
Source VulDB
Published Apr 9, 2026 at 17:00
Modified Apr 9, 2026 at 18:07

Affected Product

Vendor FoundationAgents
Product MetaGPT
Version 0.8.0
Affected Versions FoundationAgents MetaGPT 0.8.0
FoundationAgents MetaGPT 0.8.1

CWE Classification

References

💭 Join the Security Discussion

🔒 Your email address will not be published. Required fields are marked *

⚠️ Please be respectful and constructive in your comments. Security discussions should remain professional.