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.
{
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/5xxx/CVE-2026-5970.json",
"cna_assigner": "VulDB",
"cwe_ids": [
"CWE-74",
"CWE-94"
]
}{
"cpe": "cpe:2.3:a:deepwisdom:metagpt:*:*:*:*:*:*:*:*",
"extracted_events": [
{
"introduced": "0.8.0"
},
{
"last_affected": "0.8.0"
},
{
"introduced": "0.8.1"
},
{
"last_affected": "0.8.1"
},
{
"introduced": "0"
}
],
"source": [
"AFFECTED_FIELD",
"CPE_RANGE"
]
}