CVE-2026-5970mediumCWE-74CWE-94

CVE-2026-5970: medium-severity vulnerability in FoundationAgents MetaGPT

FoundationAgents MetaGPT HumanEvalBenchmark/MBPPBenchmark check_solution code injection

Published

Follow this CVE+ Monitor MetaGPT+ Monitor metagpt

E-mail alert when it lands in KEV, gets a public PoC or its score goes up.

33Vexday Risk Score

No sign of exploitation. It has a public proof of concept.

ssvc Attendcvss 6.9epss 0.4%
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/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P
Affected products
FoundationAgents · MetaGPT
⚠ Public resources, to assess the exposure of systems you control or are authorized to test. Test only with authorization.
Related CVEs — FoundationAgents MetaGPT

In the same product, most dangerous first.

CVE-2026-5972MEDIUMFoundationAgents MetaGPT terminal.py Terminal.run_command os command injectionEPSS 2.7%CVE-2026-5973MEDIUMFoundationAgents MetaGPT common.py get_mime_type os command injectionEPSS 2.6%CVE-2026-5974MEDIUMFoundationAgents MetaGPT terminal.py Bash.run os command injectionEPSS 2.6%CVE-2026-11455LOWFoundationAgents MetaGPT common.py check_cmd_exists command injectionEPSS 1.0%CVE-2026-6110MEDIUMFoundationAgents MetaGPT Tree-of-Thought Solver tot.py generate_thoughts code injectionEPSS 0.4%CVE-2026-5971MEDIUMFoundationAgents MetaGPT XML action_node.py ActionNode.xml_fill eval injectionEPSS 0.4%