Forcepoint

threat-intel

Hidden Prompts Trick AI Into False Email Summaries

Researchers at Forcepoint X-Labs demonstrated how attackers can manipulate AI-powered email summarizers by embedding malicious prompts within seemingly normal emails. The AI then generated false and altered summaries, hi…

Dark Reading · Aug 25, 2026 High

prompt injection ai security html injection

threat-intel

The browser blind spot: Why your security tool may not be blocking what you think it is [Guest Diary], (Wed, Jun 17th)

This article highlights a significant security gap in Cloud Access Security Broker (CASB) deployments due to the increasing use of the QUIC protocol. CASBs, traditionally designed to inspect TCP traffic, fail to detect w…

SANS Internet Storm Center · Jun 17, 2026 High

quic casb ssl

All articles

news.mlab.sh

Forcepoint

Hidden Prompts Trick AI Into False Email Summaries

The browser blind spot: Why your security tool may not be blocking what you think it is [Guest Diary], (Wed, Jun 17th)