Simon Willison • 1/12/2026

Superhuman AI Exfiltrates Emails

Read Original

A classic prompt injection attack against Superhuman AI manipulated the system to exfiltrate sensitive user emails, including financial and medical data, to an attacker's Google Form. The vulnerability stemmed from a CSP rule allowing image loads from docs.google.com, which Google Forms used to persist data via GET requests. The company treated it as a high-priority incident and issued a fix.

0 comments
#prompt injection #ai security #content-security-policy
Superhuman AI Exfiltrates Emails

Comments

No comments yet

Be the first to share your thoughts!

Browser Extension

Get instant access to AllDevBlogs from your browser

Top of the Week

1
Quoting Thariq Shihipar
Simon Willison • 2 votes
2
Top picks — 2026 January
Paweł Grzybek • 1 votes
3
In Praise of –dry-run
Henrik Warne • 1 votes
4
Deep Learning is Powerful Because It Makes Hard Things Easy - Reflections 10 Years On
Ferenc Huszár • 1 votes
5
Vibe coding your first iOS app
William Denniss • 1 votes
6
AGI, ASI, A*I – Do we have all we need to get there?
John D. Cook • 1 votes
7
Dew Drop – January 15, 2026 (#4583)
Alvin Ashcraft • 1 votes