CVE-2026-5970

High

Published: 09 April 2026

Published

09 April 2026

Modified

13 April 2026

KEV Added

—

Patch

—

CVSS Score 7.3 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L

EPSS Score 0.0007 22.2th percentile

Risk Priority 15 60% EPSS · 20% KEV · 20% CVSS

Summary

CVE-2026-5970 is a high-severity Injection (CWE-74) vulnerability. Its CVSS base score is 7.3 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 22.2th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.

The strongest mitigations our analysis identified are NIST 800-53 RA-5 (Vulnerability Monitoring and Scanning) and SI-10 (Information Input Validation).

Threat & Defense at a Glance

What attackers do: exploitation maps to Exploit Public-Facing Application (T1190) and 1 other technique. What defenders deploy: see the NIST 800-53 controls recommended below.

Threat & Defense Details

Mitigating Controls (NIST 800-53 r5)AI

SI-10 Information Input Validation good match

prevent

Directly prevents code injection by validating inputs to the vulnerable check_solution function in HumanEvalBenchmark/MBPPBenchmark.

SI-2 Flaw Remediation good match

prevent

Remediates the specific code injection flaw in MetaGPT up to 0.8.1 by applying patches or vendor-provided fixes when available.

RA-5 Vulnerability Monitoring and Scanning good match

detectrespond

Scans for and identifies the CVE-2026-5970 vulnerability in MetaGPT components, enabling prioritized remediation.

MITRE ATT&CK Enterprise TechniquesAI

T1190 Exploit Public-Facing Application Initial Access

Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.

attack.mitre.org →

T1059.006 Python Execution

Adversaries may abuse Python commands and scripts for execution.

attack.mitre.org →

Why these techniques?

Code injection in check_solution enables remote arbitrary Python code execution (T1059.006) via exploitation of a public-facing application (T1190).

Confidence: HIGH · MITRE ATT&CK Enterprise v18.1

NVD 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.

Deeper analysisAI

CVE-2026-5970 is a code injection vulnerability in FoundationAgents MetaGPT versions up to 0.8.1. It affects the check_solution function within the HumanEvalBenchmark and MBPPBenchmark components. Successful manipulation enables code injection, with a CVSS v3.1 base score of 7.3 (AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L), linked to CWEs-74 (Injection) and CWE-94 (Code Injection).

Remote attackers require no privileges or user interaction to exploit the vulnerability over the network with low complexity. Exploitation can result in low impacts to confidentiality, integrity, and availability through injected code execution.

The project was informed early via pull request #1988 on GitHub but has not reacted or released a patch. The exploit is public, with details documented in GitHub issue #1942 and VulDB entries at vuldb.com/vuln/356524 and vuldb.com/submit/791693.