New ChatGPhish Technique Uses Prompt Injection to Manipulate ChatGPT Responses
ID: b5c5cea6-9ecb-5284-bef2-c999d28d2d12
STIX ID: report--b5c5cea6-9ecb-5284-bef2-c999d28d2d12
Feed Name: The Cyber Express
Threat Score
Security researchers describe "ChatGPhish": a proof-of-concept browser-based prompt-injection attack where attacker-controlled content passed into ChatGPT's page-summarization feature can produce deceptive assistant outputs (phishing alerts, malicious links, or embedded QR codes) that bypass typical desktop protections and enable cross-device redirection.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.