Security researchers at Noma Labs disclosed a maximum-severity vulnerability in Ruflo, a widely used open-source AI agent platform, that left 233 Model Context Protocol (MCP) tools—including a shell-command executor—exposed over the network without any authentication by default. Tracked as CVE-2026-59726 and dubbed "RufRoot," the flaw carries a CVSS score of 10.0 and could allow a single unauthenticated HTTP request to escalate into full remote code execution.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.