How indirect prompt injection attacks on AI work - and 6 ways to shut them down ...
CVE-2026-42208 exploited within 36 hours of disclosure, exposing LiteLLM credentials, risking cloud account compromise.
Hackers rushed to target a critical LiteLLM SQL injection flaw to steal keys, credentials, and environment-variable ...
Google's security team scanned billions of web pages and found real payloads designed to trick AI agents into sending money, ...