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.
Metrics
CVSS 3.1 9.8/10
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:HWeakness enumeration
Affected software
| Vendor | Product | Versions |
|---|---|---|
| FoundationAgents | MetaGPT | 0.8.0; 0.8.1 |
References
- https://github.com/FoundationAgents/MetaGPT/Product
- https://github.com/FoundationAgents/MetaGPT/issues/1942Exploit, Issue Tracking
- https://github.com/FoundationAgents/MetaGPT/pull/1988Issue Tracking, Patch
- https://vuldb.com/submit/791693Exploit, Third Party Advisory, VDB Entry
- https://vuldb.com/vuln/356524Third Party Advisory, VDB Entry
- https://vuldb.com/vuln/356524/ctiPermissions Required, VDB Entry
Timeline
- Published
- Apr 9, 2026
- Last modified
- Oct 26, 2026
- NVD status
- Analyzed