Academy → Using HermesOfficial documentation · clear explanation

Security

الأمان

Essential32 minutes3 questions2026-08-09
The idea in one minute

Start with meaning, then move to detail.

This lesson explains Security as part of operating Hermes with explicit security boundaries. You will learn what it does, when it matters, and the smallest safe test that proves it works.

If you are new

If you are new, do not memorize names. Focus on three questions: what problem does this solve, what access does it need, and how can you verify the result?

For hands-on use

For practice, inspect the first example, identify its effects, run it on test data, and compare the result with the source claim.

For specialists

For advanced readers, inspect Overview, Dangerous Command Approval, Approval Modes, then verify failure modes and version compatibility.

What do you need first?

You only need to know which files and accounts the agent may access.

What will you know?

A clear outcome before you read.

  • Understand Security without assumed prior knowledge.
  • Separate the source description from what still needs testing in your environment.
  • Read the first command and identify its inputs and outputs before copying it.
Lesson terms

Short definitions before the details.

Gateway
The process that connects Hermes to channels such as Telegram or Discord and routes messages.
Approval & sandbox
Approval pauses a sensitive action before execution; sandboxing limits impact if something goes wrong.
Official page description

Security model, dangerous command approval, user authorization, container isolation, and production deployment best practices

Topic map

What does the source say, and in what order?

  1. 01
    Overview

    Start here to understand the core idea or structure.

  2. 02
    Dangerous Command Approval

    Read this after the foundation, then connect it to the previous step.

  3. 03
    Approval Modes

    Read this after the foundation, then connect it to the previous step.

  4. 04
    YOLO Mode

    Read this after the foundation, then connect it to the previous step.

  5. 05
    Hardline Blocklist (Always-On Floor)

    Read this after the foundation, then connect it to the previous step.

  6. 06
    User-Defined Deny Rules (approvals.deny)

    Read this after the foundation, then connect it to the previous step.

  7. 07
    Approval Timeout

    Read this after the foundation, then connect it to the previous step.

  8. 08
    What Triggers Approval

    Read this after the foundation, then connect it to the previous step.

  9. 09
    Approval Flow (CLI)

    Read this after the foundation, then connect it to the previous step.

  10. 10
    Approval Flow (Gateway/Messaging)

    Finish here to verify the result and special cases.

Examples from the official page

Copy only after you understand the effect.

approvals: mode: smart # smart | manual | off timeout: 300 # seconds to wait for user response (default: 300) cron_mode: deny # deny | approve — what cron jobs do when they hit a dangerous command mcp_reload_confirm: true # /reload-mcp asks before invalidating the MCP tool cache destructive_slash_confirm: true # /clear, /new, /reset, /undo prompt before discarding state
> /yolo ⚡ YOLO mode ON — all commands auto-approved. Use with caution. > /yolo ⚠ YOLO mode OFF — dangerous commands will require approval.
approvals: deny: - "git push --force*" - "*curl*|*sh*" - "dd if=* of=/dev/*"
Try it now

Read the first command and identify its inputs and outputs before copying it.

Match every command to your installed Hermes version, review the files and accounts it can reach, and use non-sensitive data for the first test. If this explanation differs from the source, the official source wins.

Knowledge check

Three decisions before completion.

1. What is the source of truth when “Security” changes?
2. What is the best way to apply this lesson?
3. What should happen before a step can modify files or an external account?