HIGH7.3
PYSEC-2026-2640
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.
Are you affected?
Enter the version of the package you're using.
Affected packages
PyPI/metagpt
Introduced in:
0No fixed version published yet for metagpt (pip). Pin to a known-safe version or switch to an alternative.
References
- https://nvd.nist.gov/vuln/detail/CVE-2026-5970[ADVISORY]
- https://github.com/FoundationAgents/MetaGPT/issues/1942[WEB]
- https://github.com/FoundationAgents/MetaGPT/pull/1988[WEB]
- https://github.com/FoundationAgents/MetaGPT[PACKAGE]
- https://vuldb.com/submit/791693[WEB]
- https://vuldb.com/vuln/356524[WEB]
- https://vuldb.com/vuln/356524/cti[WEB]
- https://pypi.org/project/metagpt[PACKAGE]
- https://github.com/advisories/GHSA-g977-h85w-h2xj[ADVISORY]