Microsoft Copilot AI attack took just a single click to compromise users - here's what we know

AI apps.

• Varonis discovers new prompt-injection method via malicious URL parameters, dubbed “Reprompt.”
• Attackers could trick GenAI tools into leaking sensitive data with a single click
• Microsoft patched the flaw, blocking prompt injection attacks through URLs

Security researchers Varonis have discovered Reprompt, a new way to perform prompt-injection style attacks in Microsoft Copilot which doesn’t include sending an email with a hidden prompt or hiding malicious commands in a compromised website.