CVE-2026-0760

Foundation Agents MetaGPT deserializemessage Deserialization of Untrusted Data Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of Foundation Agents MetaGPT. Authentication is not required to exploit this...

CVE-2026-0760 Foundation Agents MetaGPT deserialize_message Deserialization of Untrusted Data Remote Code Execution Vulnerability

Foundation Agents MetaGPT deserializemessage Deserialization of Untrusted Data Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of Foundation Agents MetaGPT. Authentication is not required to exploit this...

MetaGPT code injection vulnerability

MetaGPT is a multi-agent framework developed by MetaGPT Inc. MetaGPT has a code injection vulnerability, which stems from the actionoutputstrtomapping function’s lack of validation for strings provided by users. This vulnerability may lead to code injection and remote code execution...

MetaGPT code issues and vulnerabilities

MetaGPT is a multi-agent framework developed by MetaGPT Inc. There are code issues and vulnerabilities in MetaGPT; these vulnerabilities stem from the deserializemessage function’s lack of verification of the data provided by users, which may lead to the deserialization of untrusted data and remo...

CVE-2026-0760: Deserialization of Untrusted Data

Foundation Agents MetaGPT deserializemessage Deserialization of Untrusted Data Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of Foundation Agents MetaGPT. Authentication is not required to exploit this...

CVE-2026-0761: Improper Control of Generation of Code

Foundation Agents MetaGPT actionoutputstrtomapping Code Injection Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of Foundation Agents MetaGPT. Authentication is not required to exploit this vulnerability. The...

(0Day) Foundation Agents MetaGPT actionoutput_str_to_mapping Code Injection Remote Code Execution Vulnerability

This vulnerability allows remote attackers to execute arbitrary code on affected installations of Foundation Agents MetaGPT. Authentication is not required to exploit this vulnerability. The specific flaw exists within the actionoutputstrtomapping function. The issue results from the lack of prop...

PT-2026-1991

Name of the Vulnerable Software and Affected Versions Foundation Agents MetaGPT affected versions not specified Description This issue is a code injection leading to remote code execution in Foundation Agents MetaGPT. It allows attackers to execute arbitrary code on affected systems without...

(0Day) Foundation Agents MetaGPT deserialize_message Deserialization of Untrusted Data Remote Code Execution Vulnerability

This vulnerability allows remote attackers to execute arbitrary code on affected installations of Foundation Agents MetaGPT. Authentication is not required to exploit this vulnerability. The specific flaw exists within the deserializemessage function. The issue results from the lack of proper...

PT-2026-1990

Name of the Vulnerable Software and Affected Versions Foundation Agents MetaGPT affected versions not specified Description A flaw exists in the deserialize message function that allows remote attackers to execute arbitrary code on affected systems. Authentication is not required for exploitation...

EUVD-2024-0100

Malicious code in bioql PyPI...

CVE-2024-23750

MetaGPT through 0.6.4 allows the QaEngineer role to execute arbitrary code because RunCode.runscript passes shell metacharacters to subprocess.Popen...

Arbitrary Code Execution

metagpt is vulnerable to Arbitrary Code Execution. The vulnerability is due to the 'RunCode.runscript function passing shell metacharacters to subprocess.Popen caused by improper prompt santization. A user with the QaEngineer role can execute arbitrary code...

GHSA-G7PH-8423-PF4J Code execution in metagpt

MetaGPT through 0.6.4 allows the QaEngineer role to execute arbitrary code because RunCode.runscript passes shell metacharacters to subprocess.Popen...

CVE-2024-23750

MetaGPT through 0.6.4 allows the QaEngineer role to execute arbitrary code because RunCode.runscript passes shell metacharacters to subprocess.Popen...

PYSEC-2024-9

MetaGPT through 0.6.4 allows the QaEngineer role to execute arbitrary code because RunCode.runscript passes shell metacharacters to subprocess.Popen...

Design/Logic Flaw

MetaGPT through 0.6.4 allows the QaEngineer role to execute arbitrary code because RunCode.runscript passes shell metacharacters to subprocess.Popen...

PYSEC-2024-9

MetaGPT through 0.6.4 allows the QaEngineer role to execute arbitrary code because RunCode.runscript passes shell metacharacters to subprocess.Popen...

CVE-2024-23750

MetaGPT through 0.6.4 allows the QaEngineer role to execute arbitrary code because RunCode.runscript passes shell metacharacters to subprocess.Popen...

CVE-2024-23750

Summary: CVE-2024-23750 affects MetaGPT (0.6.4 and earlier). The root cause is in RunCode.run_script(), which passes shell metacharacters to subprocess.Popen, enabling arbitrary code execution by the QaEngineer role. Impact: full code execution with high severity (CVSS 3.1 base score 8.8) as indi...