Researchers Warn Copilot and Grok AI Can Be Manipulated by Prompt Injection Attacks

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

AI Assistants Exploited as Covert Command-and-Control Channels AI assistants like Grok and Microsoft Copilot can be exploited to serve as covert command-and-control (C2) channels for cybercriminals. These platforms can be manipulated to fetch attacker-controlled URLs, allowing malicious traffic to blend into normal enterprise communications. This tactic enables threat actors to relay commands to infected machines and exfiltrate stolen data. 11 sources 26