TrendAI™, the global leader in AI cybersecurity, today released new data from a global study* revealing a growing governance ...

VectorCertain LLC today announced new validation results demonstrating that its SecureAgent platform successfully detected ...

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

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

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

Google has changed Gmail, expanding Gemini to millions of users — just as it warns that this kind of AI upgrade opens the ...

ThreatDown’s EDR team discovered a sophisticated, multi-stage attack chain during an active investigation; the first documented case of attackers abusing the Deno runtime as a malware execution ...

Security researchers have discovered 10 new indirect prompt injection (IPI) payloads targeting AI agents with malicious ...

For decades, this type of no-skill hacker, known as a script kiddie, has wreaked havoc, running scripts they ripped from the ...

The Bitwarden CLI NPM package compromise is tied to a Checkmarx supply chain attack and references the Shai-Hulud worm.

Bitwarden CLI 2026.4.0 was compromised in a supply chain attack that targets crypto wallet keys, SSH keys, and CI/CD secrets.

A new wave of the Glassworm campaign is targeting the OpenVSX ecosystem with 73 "sleeper" extensions that turn malicious ...