The New Stack says attackers are inserting invisible Unicode tag characters into phishing emails—a trick that can also break AI agent pipelines that ingest untrusted text.
The New Stack reports that Microsoft built a prompt injection detector, only for it to catch a phishing campaign instead. The outlet says attackers are inserting invisible Unicode tag characters into phishing emails at massive scale. It reports that the same technique can break AI agent pipelines that ingest untrusted text.
901
1 post, first seen 1d ago
The New Stack says attackers are inserting invisible Unicode tag characters into phishing emails—a trick that can also break AI agent pipelines that ingest untrusted text.
The New Stack reports that Microsoft built a prompt injection detector, only for it to catch a phishing campaign instead. The outlet says attackers are inserting invisible Unicode tag characters into phishing emails at massive scale. It reports that the same technique can break AI agent pipelines that ingest untrusted text.
The New Stack@thenewstackMicrosoft built a prompt injection detector. Then it caught a phishing campaign instead.
Not enough discussion yet.
No sentiment analysis available yet.
Not enough discussion yet.
No sentiment analysis available yet.
—
Not ranked yet
—
Not ranked yet
The New Stack@thenewstackMicrosoft built a prompt injection detector. Then it caught a phishing campaign instead.