Riza
Provides a secure code interpreter for executing LLM-generated code, with features for creating, saving, managing, and executing code tools in an isolated en...
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Riza, derived from its capabilities.
AIVSS 5.5 · Medium
View MAESTRO 7-layer threat model →Overview
Riza MCP server executes arbitrary agent-generated code in a hardened isolated sandbox as a tool call. Arbitrary code execution is the core capability and the core risk, mitigated by Riza's isolation.
Key features
- Isolated code execution
- Multiple language runtimes
- Tool-call sandbox
Use cases
- Safe agent code execution
- Dynamic computation