Skip to content

“A prompt injection technique dubbed ChatGphish could allow…” — CyberWire Daily at 5:38

CyberWire Daily Mind the gap between IT and OT.

“A prompt injection technique dubbed ChatGphish could allow attacker-controlled web content to influence ChatGPT's responses when users request page summaries. According to permiso threat hunter Andi Amedi, hidden instructions embedded in a web page's markdown can cause the chatbot to display convincing phishing links…”

0:00 28:23