Advertisement

Threats

CANADA – 2026/04/08: In this photo illustration, the Google Antigravity logo is seen displayed on a smartphone screen. (Photo Illustration by Thomas Fuller/SOPA Images/LightRocket via Getty Images)

Vuln in Google’s Antigravity AI agent manager could escape sandbox, give attackers remote code execution

Google’s highest security setting for its agents runs command operations through a sandbox and throttles network access, but is still vulnerable to prompt injection.
Advertisement
Advertisement
Advertisement