Researchers have demonstrated that malicious instructions embedded in documents can hijack Microsoft Copilot for Word, causing it to replicate harmful content, exfiltrate data, and spread the attack t…
Microsoft spent 144 days and shipped two mitigations for a self-propagating prompt injection vulnerability in Microsoft 365 Copilot for Word, yet the exploit still worked on the day of disclosure, acc…
A proof-of-concept attack from the En Klype Salt team shows prompt-injection payloads self-replicating through Microsoft 365 Copilot in Word, propagating from one business document to another via ordi…
A security researcher demonstrated that AI worms can self-propagate through Microsoft Copilot for Word by hiding malicious instructions in documents, which Copilot then copies into new documents durin…