Researchers Show Copilot and Grok Can Be Abused as Malware C2 Proxies

"Cybersecurity researchers have disclosed that artificial intelligence (AI) assistants that support web browsing or URL fetching capabilities can be turned into stealthy command-and-control (C2) relays, a technique that could allow attackers to blend into legitimate enterprise communications and evade detection. The attack method, which has been demonstrated against Microsoft Copilot and xAI Grok, has been codenamed AI as a C2 proxy by Check Point."

"It essentially leverages Grok and Microsoft Copilot's web-browsing and URL-fetch capabilities to retrieve attacker-controlled URLs and return responses through their web interfaces, essentially transforming it into a bidirectional communication channel to accept operator-issued commands and tunnel victim data out. Notably, all of this works without requiring an API key or a registered account, thereby rendering traditional approaches like key revocation or account suspension useless."

AI assistants with web-browsing or URL-fetch capabilities can operate as stealthy command-and-control (C2) relays that blend into legitimate enterprise communications and evade detection. The technique has been demonstrated against Microsoft Copilot and xAI Grok and involves anonymous web access combined with browsing and summarization prompts. The mechanism can enable AI-assisted malware operations such as generating reconnaissance workflows, scripting attacker actions, and dynamically deciding next steps during an intrusion. Attackers can retrieve attacker-controlled URLs and return responses through the AI interfaces, creating a bidirectional channel that exfiltrates data without needing API keys or registered accounts.

Read at The Hacker News