Guides / Security operations
Checklists for teams evaluating coding agents, MCP integrations, and prompt-injection risk. Each guide links recommendations to public security guidance.
A practical baseline for limiting what coding agents can read, what they can do, and how teams review the result.
Review MCP servers, tool definitions, permissions, credentials, updates, and data flows before connecting them to a coding agent.
Understand how untrusted repository and tool content can steer coding agents, and apply controls at the action boundary.
Editorial standard
These pages provide general security guidance. They do not imply that Rechazo or a named agent implements every control. Product capabilities should be confirmed against current product documentation.