CyberRota Analysis
AI-GeneratedThe vulnerability allows unauthenticated network clients to exploit the MCPServer.startHttp() function in PraisonAI versions 1.5.0 to 1.7.2, enabling them to execute sensitive operations such as listing tools and reading resources with server-side credentials. This could lead to unauthorized data access or execution of privileged actions, posing a critical risk to any organization using affected versions. Organizations utilizing PraisonAI should prioritize upgrading to version 1.7.2 or later to mitigate this severe security threat.
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. From 1.5.0 until 1.7.2, MCPServer.startHttp() in src/praisonai-ts/src/mcp/server.ts binds without a host restriction and forwards every HTTP POST request to handleRequest() without authentication or authorization. Any network client that can reach the port can call tools/list, tools/call, resources/read, or prompts/get, causing registered handlers to run with server-side credentials and process privileges or disclose registered data. An initial remediation was released in version 1.7.2.