Vulnerability  ·  2026-08-01

Ruflo (RufRoot) MCP Bridge — Unauthenticated RCE, Credential Theft, and Agent Memory Poisoning

VulnerabilityHigh impactGlobalCVE-2026-59726
Noma Security (Noma Labs) discovered that Ruflo's MCP Bridge component, which handles all tool invocations for AI agent workflows (Codex/Claude Code hosting), was exposed without any authentication in the project's default Docker Compose configuration. A single HTTP request to the exposed bridge grants an attacker full code execution and access to agent secrets and memory.
This is a maximum-severity (CVSS 10.0) novel agent-execution attack class: unauthenticated exposure of an MCP tool-invocation bridge directly enables full agent takeover, LLM credential exfiltration, and persistent memory poisoning — a new incident-response category (memory poisoning) that traditional security tooling isn't built to detect or remediate.
A single unauthenticated HTTP POST request to the exposed MCP bridge /mcp endpoint (Express.js server on port 3001) allows an attacker to invoke any of 233 tool handlers, achieve remote code execution, steal LLM API keys, read stored user conversations, hijack running AI agents, and poison the agent's persistent memory store
Ruflo (formerly Claude Flow) AI agent orchestration platform, versions before 3.16.3
Upgrade to Ruflo 3.16.3+, which binds the bridge to loopback, gates terminal_execute behind access controls, and enables MongoDB authentication. Rotate all exposed LLM API keys and audit agent memory stores for poisoning. GHSA-c4hm-4h84-2cf3.
CSO Online — Critical Ruflo flaw lets attackers hijack AI agents through exposed MCP bridgeAI Governance InstituteHackRead — RufRoot
See this in the live feed Explore related AI security and governance findings — updated every morning.
Open the feed →