提出 #621376: agentuniverse-ai agentUniverse v0.0.18 OS Command Injection情報

タイトルagentuniverse-ai agentUniverse v0.0.18 OS Command Injection
説明Critical Remote Code Execution (RCE) vulnerabilities exist in the AgentUniverse framework's MCP (Model Context Protocol) implementation. The vulnerabilities allow arbitrary command execution through insufficient input validation in multiple components including MCPSessionManager, MCPTool, and MCPToolkit. When establishing connections to MCP servers, user-controlled input is directly passed to `StdioServerParameters` and subsequently to `anyio.open_process()` without any sanitization or validation, enabling attackers to execute arbitrary system commands with the privileges of the AgentUniverse process.
ソース⚠️ https://github.com/bayuncao-bit/vul-37
ユーザー
 bayuncao (UID 50143)
送信2025年07月23日 09:14 (9 月 ago)
モデレーション2025年08月07日 12:46 (15 days later)
ステータス承諾済み
VulDBエントリ319127 [agentUniverse 迄 0.0.18 MCPSessionManager/MCPTool/MCPToolkit StdioServerParameters 特権昇格]
ポイント20

Might our Artificial Intelligence support you?

Check our Alexa App!