How indirect prompt injection attacks on AI work - and 6 ways to shut them down

How indirect prompt injection attacks on AI work - and 6 ways to shut them down ...
The Hacker News

LiteLLM CVE-2026-42208 SQL Injection Exploited within 36 Hours of Disclosure

CVE-2026-42208 exploited within 36 hours of disclosure, exposing LiteLLM credentials, risking cloud account compromise.
SecurityWeek

Malicious AI Prompt Injection Attacks Increasing, but Sophistication Still Low: Google

Google has analyzed AI indirect prompt injection attempts involving sites on the public web and noticed an increase in ...

From XSS to RCE: How to hijack a DotNetNuke server via a single script injection

Over 750,000 websites require patching following discovery of DotNetNuke XSS vulnerability ...
Arizona Daily Star

How Trump's attacks on prosecutors build on history of using racist language and stereotypes

NEW YORK — Donald Trump’s aggressive response to his fourth criminal indictment in five months follows a strategy he has long used against legal and political opponents: relentless attacks, often ...