Gru Sandbox (gbox)
Open-source self-hostable sandbox for MCP integration and AI agent code execution.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Gru Sandbox (gbox), derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
gbox is an open-source, self-hostable sandbox for MCP integration and other AI-agent use cases, providing isolated environments for running agent-generated code. Self-hosting keeps execution on your own infrastructure; the isolation quality and egress policy are the security-defining properties.
Key features and capabilities
- Self-hostable sandbox
- MCP integration
- Isolated agent execution
Use cases
- Self-hosted code sandbox for agents
- Containing untrusted code execution