Report: Attackers Can Trick AI Assistants Into Displaying Phishing Messages
ID: da5df211-b3f9-5f1d-a79f-80135e754431
STIX ID: report--da5df211-b3f9-5f1d-a79f-80135e754431
Feed Name: KnowBe4 Blog
Threat Score
*Researchers at Permiso demonstrated a proof-of-concept "model-mediated phishing" technique in which hidden instructions embedded in benign emails cause Microsoft 365 Copilot (and similar AI assistants) to generate phishing-style summaries or include internal context, allowing attackers to craft more convincing messages or exfiltrate sensitive information.*
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.