CyberRota Analysis
AI-GeneratedPraisonAI's multi-agent teams system prior to version 1.6.59 is vulnerable due to improper binding of the ToolsMCPServer, allowing unauthenticated access to sensitive routes and registered tools. This critical flaw enables any reachable client to list and invoke tools, potentially leading to unauthorized file access, shell execution, or code execution on affected instances. Organizations using affected versions should prioritize patching to mitigate the risk of exploitation.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD Description
PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, ToolsMCPServer.run_sse and launch_tools_mcp_server bind to 0.0.0.0 and create /sse and /messages/ routes without invoking the available SecurityConfig authentication, origin-validation, or DNS-rebinding controls. Any reachable client can list and invoke registered tools, and a browser can target a local instance through DNS rebinding, with impact determined by the registered file, shell, and code-execution tools. This vulnerability is fixed in praisonaiagents 1.6.59.