Critical Ruflo flaw lets attackers hijack AI agents through exposed MCP bridge

Read more at:

The researchers said the bridge’s /mcp endpoint accepts tool invocations without authentication. In a proof-of-concept demonstration, they used Ruflo’s terminal_execute tool to obtain command execution inside the container with a single HTTP request.

“Because the MCP Bridge requires direct access to the underlying system resources to execute these commands, it creates a high-stakes security boundary,” the researchers wrote. “When an attacker can reach this endpoint without authentication, they gain a direct pipeline to the underlying host infrastructure.”

The researchers said they were able to enumerate available tools, steal LLM provider API keys from environment variables, deploy attacker-controlled AI agent swarms, retrieve user conversations stored in MongoDB, and establish persistence.

Source link

spot_img
Multi-Function Air Blower: Blowing, suction, extraction, and even inflation
spot_img

Leave a reply

Please enter your comment!
Please enter your name here