CVE-2026-5970

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.

CVSS 4.0

5.5CVSS: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

CVSS 3.1

9.8CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

EPSS

0.4% chance of exploitation in the next 30 days; higher than 32% of CVEs (scores of 2026-10-26)

CWEs

CWE-74, CWE-94

Published

2026-04-09

Modified

2026-10-26

Record from

the NVD, synced 2026-10-26

Affected

• deepwisdom:metagpt

Packages (OSV)

References

• https://github.com/FoundationAgents/MetaGPT/
• https://github.com/FoundationAgents/MetaGPT/issues/1942
• https://github.com/FoundationAgents/MetaGPT/pull/1988
• https://vuldb.com/submit/791693
• https://vuldb.com/vuln/356524

Check your stackJSON