Antigravity — Cyber Threats, Attacks & Incidents

Threat entity extracted from intelligence sources

Frequency
11
occurrences
First Seen
November 26, 2025
Last Seen
August 4, 2026

Related Threat Clusters

  • Google's Antigravity IDE Vulnerability Allows Remote Code Execution via Prompt Injection

    Researchers at Pillar Security discovered a critical prompt injection vulnerability in Google's Antigravity IDE, which allows for remote code execution (RCE) by exploiting insufficient input sanitization in the…

    4 articles · Updated April 20, 2026
  • Agent-to-Agent Exploitation Discovered in Google's ADK for Python

    Pillar Security researchers identified a vulnerability in Google's Agent Development Kit for Python (adk-python) that allows a low-privileged AI agent to trigger a high-privileged agent through prompt injection. This…

    8 articles · Updated August 3, 2026
  • Sandbox Escapes Discovered in Major AI Coding Tools

    Pillar Security has identified vulnerabilities in four AI coding agents—Cursor, Codex, Gemini CLI, and Antigravity—that allow for sandbox escapes without direct attacks on the sandbox itself. These vulnerabilities stem…

    6 articles · Updated July 20, 2026
  • Google Launches CodeMender to Automate Code Vulnerability Remediation

    On July 21, 2026, Google announced the preview release of CodeMender, a managed AI security agent designed to identify and remediate software vulnerabilities. Integrated into the Gemini Enterprise Agent Platform and AI…

    8 articles · Updated July 21, 2026
  • Amazon AWS Outage Linked to AI Tool Misconfiguration

    In December 2025, an Amazon Web Services (AWS) outage lasting 13 hours was reportedly caused by the Kiro AI coding tool, which autonomously deleted and recreated a production environment. Amazon attributed the incident…

    3 articles · Updated May 5, 2026
  • Google's Antigravity AI Tool Hacked Day After Launch

    A security researcher identified a significant flaw in Google's newly launched Antigravity AI coding tool just one day after its release. This incident exemplifies the trend of companies rapidly deploying AI tools that…

    2 articles · Updated November 27, 2025

Recent Intelligence Reports

  • Google's AI Agent Development Kit Flaw Allows Privilege Escalation, Malicious Issues Can ... — Finance.Biggo · August 4, 2026
  • Week of Sandbox Escapes — www.pillar.security · July 21, 2026
  • Now in preview: Find and fix software vulnerabilities with CodeMender — Cloud.Google · July 21, 2026
  • AI agents can escape sandboxes without ever breaking them — Csoonline · July 21, 2026
  • Prompt Injection Leads To Rce And Sandbox Escape In Antigravity — www.pillar.security · July 21, 2026
  • Cursor, Codex, Gemini CLI, Antigravity hit by sandbox escapes — Aiweekly.Co · July 21, 2026
  • The EU AI Act is Not Ready for Agents — Techpolicy.Press · May 5, 2026
  • Google Fixes Critical RCE Flaw in AI — Darkreading · April 21, 2026

CVSS v3.1 Breakdown