CVE-2026-5970: Code Injection in FoundationAgents MetaGPT
CVE-2026-5970 is a medium severity code injection vulnerability in FoundationAgents MetaGPT versions up to 0. 8. 1. It affects the check_solution function within the HumanEvalBenchmark/MBPPBenchmark component. The vulnerability allows remote attackers to inject code by manipulating inputs to this function. Although the issue was reported early via a pull request, the vendor has not yet issued a fix or official remediation. Exploit details are publicly available, but no known exploits in the wild have been confirmed.
AI Analysis
Technical Summary
This vulnerability in FoundationAgents MetaGPT (<= 0.8.1) involves code injection through the check_solution function of the HumanEvalBenchmark/MBPPBenchmark component. An attacker can remotely manipulate inputs to execute arbitrary code. The CVSS 4.0 base score is 6.9 (medium severity), reflecting network attack vector, low complexity, no privileges or user interaction required, and low to limited impact on confidentiality, integrity, and availability. No patch or official remediation has been released as of the publication date, and the vendor has not responded to the initial report.
Potential Impact
Successful exploitation could allow remote attackers to execute arbitrary code within the context of the vulnerable component, potentially compromising system integrity and confidentiality. The impact is rated medium due to limited scope and partial impact on confidentiality, integrity, and availability. No active exploitation in the wild has been reported yet.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Since no official fix or temporary workaround has been published and the vendor has not reacted, users should consider restricting network access to the vulnerable component and monitor for suspicious activity related to this function until a patch is available.
CVE-2026-5970: Code Injection in FoundationAgents MetaGPT
Description
CVE-2026-5970 is a medium severity code injection vulnerability in FoundationAgents MetaGPT versions up to 0. 8. 1. It affects the check_solution function within the HumanEvalBenchmark/MBPPBenchmark component. The vulnerability allows remote attackers to inject code by manipulating inputs to this function. Although the issue was reported early via a pull request, the vendor has not yet issued a fix or official remediation. Exploit details are publicly available, but no known exploits in the wild have been confirmed.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
This vulnerability in FoundationAgents MetaGPT (<= 0.8.1) involves code injection through the check_solution function of the HumanEvalBenchmark/MBPPBenchmark component. An attacker can remotely manipulate inputs to execute arbitrary code. The CVSS 4.0 base score is 6.9 (medium severity), reflecting network attack vector, low complexity, no privileges or user interaction required, and low to limited impact on confidentiality, integrity, and availability. No patch or official remediation has been released as of the publication date, and the vendor has not responded to the initial report.
Potential Impact
Successful exploitation could allow remote attackers to execute arbitrary code within the context of the vulnerable component, potentially compromising system integrity and confidentiality. The impact is rated medium due to limited scope and partial impact on confidentiality, integrity, and availability. No active exploitation in the wild has been reported yet.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Since no official fix or temporary workaround has been published and the vendor has not reacted, users should consider restricting network access to the vulnerable component and monitor for suspicious activity related to this function until a patch is available.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulDB
- Date Reserved
- 2026-04-09T12:04:16.831Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 69d7ee091cc7ad14da04a8dd
Added to database: 4/9/2026, 6:20:57 PM
Last enriched: 4/9/2026, 6:36:03 PM
Last updated: 4/9/2026, 8:40:03 PM
Views: 5
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.