---
id: CVE-2026-5970
aliases:
  - GHSA-g977-h85w-h2xj
  - PYSEC-2026-2640
title: MetaGPT has an Injection issue
summary: MetaGPT has an Injection issue
severity: high
cvss: 7.3
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L'
vendor: metagpt
product: metagpt
ecosystem: pip
affected:
  - metagpt <= 0.8.1
published: '2026-04-09'
updated: '2026-07-13'
source: OSV
sourceUrl: 'https://osv.dev/vulnerability/GHSA-g977-h85w-h2xj'
references:
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2026-5970'
  - url: 'https://github.com/FoundationAgents/MetaGPT/issues/1942'
  - url: 'https://github.com/FoundationAgents/MetaGPT/pull/1988'
  - url: 'https://github.com/FoundationAgents/MetaGPT'
  - url: 'https://vuldb.com/submit/791693'
  - url: 'https://vuldb.com/vuln/356524'
  - url: 'https://vuldb.com/vuln/356524/cti'
tags:
  - osv
  - pip
epss: 0.00713
epssPercentile: 0.51575
ingestedAt: '2026-07-13T18:57:58.188Z'
---

## Overview

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 packages

- `metagpt <= 0.8.1`

## Remediation

Refer to the advisory for the patched release.