Vulnerability Description
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.
CVSS Score
HIGH
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Deepwisdom | Metagpt | <= 0.8.1 |
Related Weaknesses (CWE)
References
- https://github.com/FoundationAgents/MetaGPT/Product
- https://github.com/FoundationAgents/MetaGPT/issues/1942Issue TrackingExploit
- https://github.com/FoundationAgents/MetaGPT/pull/1988Issue TrackingPatch
- https://vuldb.com/submit/791693ExploitThird Party AdvisoryVDB Entry
- https://vuldb.com/vuln/356524Third Party AdvisoryVDB Entry
- https://vuldb.com/vuln/356524/ctiPermissions RequiredVDB Entry
FAQ
What is CVE-2026-5970?
CVE-2026-5970 is a vulnerability with a CVSS score of 7.3 (HIGH). 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 c...
How severe is CVE-2026-5970?
CVE-2026-5970 has been rated HIGH with a CVSS base score of 7.3/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-5970?
Check the references section above for vendor advisories and patch information. Affected products include: Deepwisdom Metagpt.