#MCP
Inside NadMesh: The Shodan-Powered Botnet Hunting Exposed AI Servers
Researchers at XLab have identified NadMesh, a Go-based botnet that uses Shodan to hunt down exposed AI and MCP infrastructure before hijacking it with more than 20 exploitation...
Hackers Can Hijack Claude Code MCP Traffic to Steal OAuth Tokens — No Patch Coming
Researchers at Mitiga Labs demonstrated a five-step npm supply chain attack that rewrites ~/.claude.json to redirect Claude Code MCP traffic through attacker-controlled infrastructure, silently capturing OAuth tokens for...
BadHost (CVE-2026-48710): Critical Authentication Bypass Threatens Thousands of AI Agent Applications
A newly disclosed critical vulnerability dubbed 'BadHost' (CVE-2026-48710) enables attackers to bypass authentication in FastAPI and Starlette-based AI applications through manipulated HTTP Host headers. Thousands of LLM inference...