Vulnerability  ·  2026-07-31

Ruflo AI Agent Platform 'RufRoot' - Unauthenticated MCP Bridge Enables RCE, Credential Theft, and AI Memory Poisoning

VulnerabilityHigh impactGlobalCVE-2026-59726
This is a maximum-severity (CVSS 10.0), unauthenticated remote code execution vulnerability in a widely-deployed agentic AI platform reachable directly over the network in default configurations. Beyond RCE, the flaw specifically enables 'AI memory poisoning' — corrupting the persistent memory/learning pipeline that agents rely on for context — which can persist malicious instructions across future agent sessions, a novel and severe agentic attack class.
Ruflo's MCP Bridge component exposed an unauthenticated POST /mcp endpoint on port 3001 (bound to 0.0.0.0 in default Docker deployments), exposing 233 MCP tools without authentication. An unauthenticated remote attacker could invoke terminal_execute to run arbitrary commands inside the bridge container, steal LLM API keys, read/poison agent conversation history stored in an unauthenticated MongoDB instance, and establish persistent backdoors across an enterprise's agent fleet.
Ruflo (open-source AI agent hosting platform) versions prior to 3.16.3
Upgrade to Ruflo 3.16.3 or later, which binds the MCP bridge to loopback by default, gates terminal_execute behind server-side controls, and enables MongoDB authentication. Restrict network access to MCP bridges, rotate all LLM API keys, and audit AgentDB/conversation stores for tampering.
The Hacker News - Ruflo MCP Flaw Lets Unauthenticated Attackers Run Commands and Poison AI MemoryCSO Online - Critical Ruflo flaw lets attackers hijack AI agents through exposed MCP bridge
See this in the live feed Explore related AI security and governance findings — updated every morning.
Open the feed →