System Architecture Diagram

End-to-end request flow from the dashboard through security, intent routing, command generation, remote execution, and audit logging.

ShellSentry system architecture: user request flows through web API, security, intent routing, natural language to Bash generation or built-in safe actions, SSH execution on remote Linux servers, results returned to the user, and audit logging.
Solid arrows show execution flow; dashed arrows show audit logging paths.

Interactive Workflow

  1. 1. Authentication

    Session-protected access ties actions to signed-in users for accountability.

  2. 2. Request and targets

    Users submit a natural language task and optionally select servers; otherwise configured defaults apply.

  3. 3. Input security validation

    The security layer screens unsafe patterns and policy violations before any routing or generation.

  4. 4. Intent routing (safe modes)

    Safe Cron intents (list or schedule managed entries) and Script Archive intents (list, rerun, explain) short-circuit to dedicated SSH helpers when matched.

  5. 5. Host probe and RAG

    For standard NL-to-Bash, each host is probed in parallel for OS, services, and sockets; trusted examples may be retrieved to ground the LLM prompt.

  6. 6. LLM generation and cleanup

    An OpenAI-compatible model proposes commands per host context; markdown wrappers and unsafe prompt leakage are stripped.

  7. 7. Command validation

    Whitelist, blacklist, read-only rules, and normalization gate execution and shape the final command string.

  8. 8. Parallel SSH execution

    Paramiko runs approved commands independently per host; multi-line scripts are archived remotely before execution when applicable.

  9. 9. Reporting and audit

    Structured JSON includes summaries and technical reports, optional AI explanations, and persistent execution logging for review.