Connect your agent
AdvisoriesCriticalCheck your lockfilePluginHow it worksPricing Connect your agent

Advisory record · GHSA-g977-h85w-h2xj

MetaGPT has an Injection issue

CVSS 6.9 MediumEPSS 0.0040 · 35th percentile

Published by the GitHub Advisory Database at 9 Apr 2026, 18:31 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
metagptPyPI<=0.8.1No fixed version yet
Identifiers
GHSA-g977-h85w-h2xj · CVE-2026-5970 · PYSEC-2026-2640
Weakness (CWE)
CWE-74 · CWE-94
Tags
Published
9 Apr 2026
Updated
13 Jul 2026

Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

MetaGPT versions up to and including 0.8.1 are affected. The flaw is in the check_solution function of the HumanEvalBenchmark and MBPPBenchmark components, and a manipulation there can lead to code injection that can be triggered remotely. A public exploit exists. No fix is listed, and the source gives few details on the exact input that triggers the issue.

Written 6 Nov 2026.

Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

Severity and exploitation

ScoreRatingCVSSVectorSource
6.9 Medium 4.0 CVSS: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 CNA (VulDB)
  • CISA KEV Not listed.
  • EPSS 0.0040, the 35th percentile, on 14 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

  1. 31 Oct 2026, 15:02 UTC First seen by agentprime
  2. 31 Oct 2026, 15:02 UTC Confirmed by OSV

Sources

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.