EUVD-2026-20984

A vulnerability was detected in FoundationAgents MetaGPT up to 0.8.1. This affects the function checksolution 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. Th...

GHSA-3GHP-8R47-4GJ4 FoundationAgents MetaGPT vulnerable to eval injection

A flaw has been found in FoundationAgents MetaGPT up to 0.8.1. This vulnerability affects the function ActionNode.xmlfill of the file metagpt/actions/actionnode.py of the component XML Handler. Executing a manipulation can lead to improper neutralization of directives in dynamically evaluated cod...

CVE-2026-5971

A flaw has been found in FoundationAgents MetaGPT up to 0.8.1. This vulnerability affects the function ActionNode.xmlfill of the file metagpt/actions/actionnode.py of the component XML Handler. Executing a manipulation can lead to improper neutralization of directives in dynamically evaluated cod...

CVE-2026-5970

A vulnerability was detected in FoundationAgents MetaGPT up to 0.8.1. This affects the function checksolution 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. Th...

Arbitrary Code Injection

Overview metagpt is a The Multi-Agent Framework Affected versions of this package are vulnerable to Arbitrary Code Injection via the checksolution function in the HumanEvalBenchmark/MBPPBenchmark component. An attacker can execute arbitrary code by sending specially crafted input remotely...

CVE-2026-5971 FoundationAgents MetaGPT XML action_node.py ActionNode.xml_fill eval injection

A flaw has been found in FoundationAgents MetaGPT up to 0.8.1. This vulnerability affects the function ActionNode.xmlfill of the file metagpt/actions/actionnode.py of the component XML Handler. Executing a manipulation can lead to improper neutralization of directives in dynamically evaluated cod...

CVE-2026-5971 FoundationAgents MetaGPT XML action_node.py ActionNode.xml_fill eval injection

A flaw has been found in FoundationAgents MetaGPT up to 0.8.1. This vulnerability affects the function ActionNode.xmlfill of the file metagpt/actions/actionnode.py of the component XML Handler. Executing a manipulation can lead to improper neutralization of directives in dynamically evaluated cod...

CVE-2026-5971

A flaw has been found in FoundationAgents MetaGPT up to 0.8.1. This vulnerability affects the function ActionNode.xmlfill of the file metagpt/actions/actionnode.py of the component XML Handler. Executing a manipulation can lead to improper neutralization of directives in dynamically evaluated cod...

CVE-2026-5971

FoundationAgents MetaGPT up to 0.8.1 is affected. The vulnerability lies in ActionNode.xml_fill within metagpt/actions/action_node.py (XML Handler). It enables remote exploitation through manipulation of dynamically evaluated code, with reports that an exploit has been published. Multiple sources...

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

A vulnerability was detected in FoundationAgents MetaGPT up to 0.8.1. This affects the function checksolution 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. Th...

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

A vulnerability was detected in FoundationAgents MetaGPT up to 0.8.1. This affects the function checksolution 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. Th...

CVE-2026-5970

FoundationAgents MetaGPT up to 0.8.1 is affected by a vulnerability in the check_solution function of HumanEvalBenchmark/MBPPBenchmark. A manipulation can cause code injection, with a remote attack potential. The exploit is public, and the project was informed via a pull request but has not respo...

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

A vulnerability was detected in FoundationAgents MetaGPT up to 0.8.1. This affects the function checksolution 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. Th...

CVE-2026-5970

A vulnerability was detected in FoundationAgents MetaGPT up to 0.8.1. This affects the function checksolution 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. Th...

MetaGPT 安全漏洞

MetaGPT is a multi-agent framework developed by MetaGPT Inc. Versions of MetaGPT 0.8.1 and earlier contained security vulnerabilities. These vulnerabilities were caused by operations on the ActionNode.xmlfill function in the XML Handler component, which could lead to improper instructions in...

MetaGPT 操作系统命令注入漏洞

MetaGPT is a multi-agent framework developed by MetaGPT Inc. Versions of MetaGPT 0.8.1 and earlier contained a vulnerability related to operating system command injection. This vulnerability stemmed from the Bash.run function in the metagpt/tools/libs/terminal.py library, which could allow attack...

PT-2026-31707

Name of the Vulnerable Software and Affected Versions FoundationAgents MetaGPT versions up to 0.8.1 Description A flaw exists in the Terminal.run command function within the metagpt/tools/libs/terminal.py library. This allows for os command injection, potentially enabling remote exploitation. The...

MetaGPT 代码注入漏洞

MetaGPT is a multi-agent framework developed by MetaGPT Inc. Versions of MetaGPT 0.8.1 and earlier contained a code injection vulnerability. This vulnerability stemmed from operations on the checksolution function within the HumanEvalBenchmark/MBPPBenchmark component, which could lead to code...

PT-2026-31679

Name of the Vulnerable Software and Affected Versions FoundationAgents MetaGPT versions prior to 0.8.2 Description A flaw in the XML Handler component allows remote attackers to cause improper neutralization of directives in dynamically evaluated code. This issue occurs within the ActionNode.xml...

MetaGPT 操作系统命令注入漏洞

MetaGPT is a multi-agent framework developed by MetaGPT Inc. Versions of MetaGPT 0.8.1 and earlier contained a vulnerability related to operating system command injection. This vulnerability stemmed from the Terminal.runcommand function in the metagpt/tools/libs/terminal.py library, which could...