AI browsers can be convenient, but they also come with security risks.

Claude for Chrome v1.0.80 still accepts forged clicks from other extensions, triggering Gmail, Docs, and Calendar tasks ...

A new attack technique dubbed HalluSquatting turns AI assistants’ tendency to hallucinate into a scalable infection vector.

The U.S. Cybersecurity and Infrastructure Security Agency (CISA) is warning that attackers are exploiting vulnerabilities in ...

JFrog finds 148 npm proxy packages turned student browsers into a DDoS botnet, while a mutable loader lets operators re-arm ...

Rogue Agent, a vulnerability in Google Cloud Dialogflow CX, allowed attackers to control agents and exfiltrate sensitive data.

To defend against slopsquatting, proactive trust verification must occur before any dependency lands in a developer's hands.

Indirect prompt injection attacks are now draining cryptocurrency from AI agents in production. Zscaler ThreatLabz documented ...

Learn why production AI agents need agentic infrastructure for durable execution, state, memory, approvals, observability, ...

As the US-Israeli war with Iran continues to impact and shape the region, journalists from RFE/RL's Central Newsroom and Iranian service, Radio Farda, deliver ongoing updates and analysis. US Central ...