CVE-2026-5970

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

VendorProductVersion RangeStatus
FoundationAgentsMetaGPT0.8.0affected
FoundationAgentsMetaGPT0.8.1affected

Weaknesses

  • CWE-94: Code Injection
  • CWE-74: Injection

ADP Enrichment

CISA ADP Vulnrichment

  • SSVC:
  • Exploitation: poc
    • Automatable: yes
    • Technical Impact: partial

References