by Kastro
Paper/Archive/CVE-2026-5970

CVE-2026-5970

FoundationAgents MetaGPT — FoundationAgents MetaGPT HumanEvalBenchmark/MBPPBenchmark check_solution code injection

EPSS 0.4%public exploitCVSS 9.8
critical.is priorityof 100
46
CVSS 9.8 (NVD)9.8 / 10 × 3029.4Not in CISA KEV+300.0EPSS percentile 32.8.328 × 206.6Exploit: SSVC poc+1010.0SSVC exploitation: poc+100.0
Description · from the CVE record

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.

Affected

ProductAffectedFixed inSource
MetaGPT0.8.0–CNA
MetaGPT0.8.1–CNA

Scores by source

NVD9.8CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
VulDB (CNA)7.3CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R
VulDB (CNA)7.3CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R
VulDB (CNA)6.9CVSS: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
CISA ADPSSVCExploitation: poc · Automatable: yes · Technical impact: partial

References

writeupvuldb.com/vuln/356524refvuldb.com/vuln/356524/ctiwriteupvuldb.com/submit/791693exploitgithub.com/FoundationAgents/MetaGPT/issues/1942patchgithub.com/FoundationAgents/MetaGPT/pull/1988refgithub.com/FoundationAgents/MetaGPT