CVE-2026-5970
6.9
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
Summary
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.
Affected Software
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| FoundationAgents | MetaGPT | 0.8.0 | affected |
| FoundationAgents | MetaGPT | 0.8.1 | affected |
Weaknesses
- CWE-94: Code Injection
- CWE-74: Injection
ADP Enrichment
CISA ADP Vulnrichment
- SSVC:
- Exploitation: poc
- Automatable: yes
- Technical Impact: partial
References
- https://vuldb.com/vuln/356524
- https://vuldb.com/vuln/356524/cti
- https://vuldb.com/submit/791693
- https://github.com/FoundationAgents/MetaGPT/issues/1942
- https://github.com/FoundationAgents/MetaGPT/pull/1988
- https://github.com/FoundationAgents/MetaGPT/
Feedback
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.