Arbitrary Command Injection

Overview metagpt is a The Multi-Agent Framework Affected versions of this package are vulnerable to Arbitrary Command Injection via the Bash.run method in metagpt/tools/libs/terminal.py. An attacker can execute arbitrary operating system commands by supplying crafted input remotely. Remediation A...

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...