CVE-2026-5970: FoundationAgents MetaGPT HumanEvalBenchmark/MBPPBenchmark check_solution code injection
A vulnerability was detected in FoundationAgents MetaGPT up to 0.8.1. This affects the function checksolution 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.
Affected Software
Remediation
Patch Available
Event History
Frequently Asked Questions
What is the severity of CVE-2026-5970?
CVE-2026-5970 has been classified with a significant severity due to its potential for code injection.
How do I fix CVE-2026-5970?
To fix CVE-2026-5970, upgrade FoundationAgents MetaGPT to version 0.8.2 or later where the vulnerability is addressed.
Which versions of FoundationAgents MetaGPT are affected by CVE-2026-5970?
CVE-2026-5970 affects FoundationAgents MetaGPT versions up to and including 0.8.1.
What component is affected by CVE-2026-5970?
CVE-2026-5970 specifically affects the check_solution function in the HumanEvalBenchmark/MBPPBenchmark component.
What type of vulnerability is CVE-2026-5970?
CVE-2026-5970 is classified as a code injection vulnerability.