AI Chat Assistants Could Serve as Stealthy Malware C2 Relays

Cybersecurity researchers warn that AI assistants with web-browsing capabilities (such as Microsoft Copilot and xAI Grok) can be hijacked as stealthy, bidirectional command-and-control relays. By feeding crafted prompts, attackers can issue commands to a compromised host and exfiltrate data via trusted AI services, effectively turning living-off-trusted-sites (LOTS) into C2 channels and enabling AI-assisted malware operations and real-time evasion, without requiring API keys.