Vuln in Google’s Antigravity AI agent manager could escape sandbox, give attackers remote code execution
Summary
Google’s highest security setting for its agents runs command operations through a sandbox and throttles network access, but is still vulnerable to prompt inj...
Description
Google’s highest security setting for its agents runs command operations through a sandbox and throttles network access, but is still vulnerable to prompt inj...
Original reporting
AFBytes is a read-only aggregator. Use the original source for full context and complete reporting.
Open original source