Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1336 CNY

100%
Buy Us a Coffee

CVE-2026-5970— FoundationAgents MetaGPT HumanEvalBenchmark/MBPPBenchmark check_solution code injection

Quick assessment

Affected
FoundationAgents MetaGPT
Exploitation
Public or AI PoC available; prioritize validation
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

MetaGPT是MetaGPT公司的一个多代理框架。 MetaGPT 0.8.1及之前版本存在代码注入漏洞，该漏洞源于对HumanEvalBenchmark/MBPPBenchmark组件中check_solution函数的操作，可能导致代码注入攻击。

CVSS 7.3 · High EPSS 0.39% · P32

Possible ATT&CK Techniques 1 AI

T1190 · Exploit Public-Facing Application
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-5970

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
FoundationAgents MetaGPT HumanEvalBenchmark/MBPPBenchmark check_solution code injection
Source: CVE Program / CVE List V5
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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L
Source: CVE Program / CVE List V5
Vulnerability Type
对生成代码的控制不恰当(代码注入)
Source: CVE Program / CVE List V5
Vulnerability Title
MetaGPT 代码注入漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
MetaGPT是MetaGPT公司的一个多代理框架。 MetaGPT 0.8.1及之前版本存在代码注入漏洞，该漏洞源于对HumanEvalBenchmark/MBPPBenchmark组件中check_solution函数的操作，可能导致代码注入攻击。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
FoundationAgents MetaGPT 0.8.0 -

II. Public POCs for CVE-2026-5970

# POC Description Source Link Shenlong Link
AI-Generated POC Premium
Qwen3.6-35B-A3B · 8490 chars
Pro+ exclusive includes:
Vulnerability reproduction recording (real sandbox build + trigger, exclusive)
In-depth vulnerability mechanism
Trigger conditions & impact
Full executable POC code
Exploit chain & mitigation
POC zip download
100+ AI POC generations per month

III. Intelligence Information for CVE-2026-5970

请登录查看更多情报信息。

Patches & Fixes for CVE-2026-5970 (1)

Proof of Concept for CVE-2026-5970 (1)

Same Patch Batch · FoundationAgents · 2026-04-09 · 5 CVEs total

CVE-2026-5971 7.3 HIGH FoundationAgents MetaGPT XML action_node.py ActionNode.xml_fill eval injection
CVE-2026-5973 7.3 HIGH FoundationAgents MetaGPT common.py get_mime_type os command injection
CVE-2026-5972 7.3 HIGH FoundationAgents MetaGPT terminal.py Terminal.run_command os command injection
CVE-2026-5974 7.3 HIGH FoundationAgents MetaGPT terminal.py Bash.run os command injection

IV. Related Vulnerabilities

Same product: MetaGPT
Same vendor: FoundationAgents
Same weakness: CWE-94

V. Comments for CVE-2026-5970

No comments yet

Leave a comment