Google Threat Intelligence and Wiz Attack Surface Management have begun integration to help organizations prioritize security risks by matching real-world exposures with real-time adversary activity. …
The Department of Homeland Security demonstrated to lawmakers how jailbroken AI models can generate detailed bomb-building and terror attack plans in minutes, bypassing safety guardrails. The closed-d…
Google's Threat Intelligence team found that prompt injection attacks on AI agents are increasing but largely ineffective due to agents' own incompetence. Indirect prompt injection, where malicious in…
The House Homeland Security Subcommittee on Cybersecurity and Infrastructure Protection will hold a hearing on June 4 examining how frontier AI models impact cybersecurity, including both defensive be…
As AI coding agents become deeply embedded in developer workflows, the attack surface now extends beyond source code to include repository files, agent instructions, runtime settings, and extension pa…