← Back to CVEs

CVE-2026-5970

HIGH

7.3

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.

CVE Details

CVSS v3.1 Score7.3

SeverityHIGH

CVSS VectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L

Attack VectorNETWORK

ComplexityLOW

Privileges RequiredNONE

User InteractionNONE

Published4/9/2026

Last Modified4/9/2026

Sourcenvd

Honeypot Sightings0

Weaknesses (CWE)

CWE-74CWE-94

References

https://github.com/FoundationAgents/MetaGPT/(cna@vuldb.com)

https://github.com/FoundationAgents/MetaGPT/issues/1942(cna@vuldb.com)

https://github.com/FoundationAgents/MetaGPT/pull/1988(cna@vuldb.com)

https://vuldb.com/submit/791693(cna@vuldb.com)

https://vuldb.com/vuln/356524(cna@vuldb.com)

https://vuldb.com/vuln/356524/cti(cna@vuldb.com)

IOC Correlations

No correlations recorded

This product uses data from the NVD API but is not endorsed or certified by the NVD.