Skip to content
Submit incident
AII-1001-49037
ReportedReported by fewer than three independent publishers, with no official finding.

Google Antigravity IDE persistent code execution vulnerability

Mindgard discovered a vulnerability in Google's newly launched Antigravity IDE that allows a malicious trusted workspace to embed a persistent backdoor for arbitrary code execution across all future sessions. The backdoor persists even after uninstalling and reinstalling the application, creating cross-workspace security risks.

19 November 2025 Β· Google Β· Security and cyberattacks
19 November 2025
AII-1001-490373 sources ↓
Quick facts
Category
Security and cyberattacks
Country
United States
Source
forbes.com
Date
19 November 2025
Drafted by
Raidu Incident Detection

What happened

Within 24 hours of launch, Mindgard identified a vulnerability in Google's Antigravity IDE where a malicious "trusted workspace" can embed a persistent backdoor to execute arbitrary code.

The backdoor executes on any future application launch, even when no specific project is opened, and persists even after complete uninstall and reinstall of Antigravity.

Because Antigravity requires trusted workspace access by design, a compromised workspace creates cross-workspace risk, affecting all subsequent use of Antigravity regardless of trust settings.

Classification

Category
Security and cyberattacks
Country
United States
Harm status
Potential harm
Intent
Unknown
Timing
Post-deployment
Harmed
Business
Consequences
None recorded
AI systems
Antigravity IDE

Sources and evidence

This record was researched and written by the Index, based on the following original reporting.

forbes.com
Forbes: Google’s Hot New AI Coding Tool Was Hacked A Day After Launch
mindgard.ai
Google Antigravity IDE persistent code execution vulnerability
mindgard.ai
Mindgard Disclosure