Advisory

PYSEC-2026-2640

Also known as: CVE-2026-5970, GHSA-g977-h85w-h2xj

Summary

MetaGPT has an Injection issue

Details

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.

Severity

High Basis: CVSS v3 score 7.3, vector CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L

Dates

Published
2026-07-13 14:36 UTC
Modified
2026-07-13 16:32 UTC

Affected packages and fixes

metagpt

PyPI · All systems

Affected

  • introduced 0, last affected 0.8.1 (ecosystem)

Fixed versions

None listed

Fix

No fixed version is listed.

Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.

Check your own computer: guard packages check

View this record on OSV.dev

Source

Source: PyPA Advisory Database · CC BY 4.0

Sources & licences