Analysis · curated 15 Jul 2026

Mitigate indirect prompt injection risks from Google Cloud MCP | Google Cloud Data Agent Kit extension for Antigravity IDE | Google Cloud Documentation

Coverage timeline

15 Jul 2026google.com 29 Jul 2026google.com 22 Aug 2026google.com

Why it matters

Coding agents run with the full delegated privileges of their user, so indirect prompt injection through MCP-accessed data can drive them to compromise infrastructure and exfiltrate data, making these vendor-recommended guardrails important for defenders deploying AI coding agents.

Google Cloud documentation for the Data Agent Kit extension (VS Code and Antigravity IDE) warns that coding agents connected via Google Cloud MCP can be hijacked through indirect prompt injection, where malicious instructions hidden in data sources such as Cloud Storage, BigQuery, email, or calendars are interpreted as commands. The guidance recommends mitigations including running agents in constrained environments like Cloud Workstations with disabled internet access and no root privileges.