CVE-2026-5970: MetaGPT has an Injection issue
A vulnerability was detected in FoundationAgents MetaGPT up to 0.8.1. This affects the function checksolution 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.
Published Apr 9, 2026 · Updated May 6, 2026
Affected packages
metagpt
- Ecosystem
- PyPI
- Affected
- <= 0.8.1
- Fixed in
- No patched version yet
- Check
pip show metagpt
Advisory details
From the GitHub Advisory Database (CC BY 4.0).
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.
References
- https://nvd.nist.gov/vuln/detail/CVE-2026-5970
- https://github.com/FoundationAgents/MetaGPT/issues/1942
- https://github.com/FoundationAgents/MetaGPT/pull/1988
- https://github.com/FoundationAgents/MetaGPT
- https://vuldb.com/submit/791693
- https://vuldb.com/vuln/356524
- https://vuldb.com/vuln/356524/cti
- https://github.com/advisories/GHSA-g977-h85w-h2xj
How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology
More PyPI vulnerabilities
All PyPI entriesCVE-2026-10566
FoundationAgents MetaGPT: Deserialization through flawed argument mapping via Message.check_instruct_content()
low5.3No fixJun 2, 2026CVE-2026-6109
MetaGPT has an eval injection via a cross-site request forgery attack
low4.3No fixApr 12, 2026CVE-2026-6110
MetaGPT has an eval injection in metagpt/strategy/tot.py
medium7.3No fixApr 12, 2026CVE-2026-6111
MetaGPT affected by server-side request forgery in metagpt/utils/common.py
low6.3No fixApr 12, 2026CVE-2026-5971
FoundationAgents MetaGPT vulnerable to eval injection
medium7.3No fixApr 9, 2026CVE-2026-5972
FoundationAgents MetaGPT vulnerable to os command injection via the Terminal.run_command
medium7.3Apr 9, 2026
