Researchers show AI assistants can act as stealth C2 proxies, enabling malware communication, evasion, and runtime attack automation.
Researchers warn that AI assistants like Copilot and Grok can be manipulated through prompt injections to perform unintended actions.
Grok 4.2 has no memory, so each prompt needs full context; use reasoning traces and source priority for clearer results.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results