Receber por email
← Voltar para o catálogo

ImmyBot Script Execution

Use this skill when working with ImmyBot's PowerShell script library — searching scripts by name or category, validating script syntax, executing a script in SYSTEM context on a target computer, and reviewing execution history and results. Script execution is a destructive, highly privileged operation that requires explicit confirmation.

31estrelas
Atualizado há 4 meses

Ver no GitHub ↗ Licença: Apache-2.0

Como adicionar

/plugin marketplace add wyre-technology/msp-claude-plugins

O comando exato pode variar conforme o repositório. Confira o README no GitHub.

Para o autor da skill

Cole no README do seu repo

Mostra que sua skill está catalogada na Skillteca, gera backlink e tráfego rastreável.

[![Skillteca](https://www.skillteca.com.br/api/badge/immybot-script-execution/svg)](https://www.skillteca.com.br/skills/immybot-script-execution)

Skills relacionadas

Ver todas de Documentos →

Alerta por categoria

Receba novas skills de Documentos toda segunda

1 email curto, só com as skills novas de Documentos. 4 minutos de leitura, sem spam, cancela com 1 clique.

Você confirma o email no primeiro envio. Sem spam. Cancela com 1 clique.

Ler descrição completa

ImmyBot Script Execution

ImmyBot ships a PowerShell script library that runs against managed endpoints in SYSTEM context. This is a privileged, destructive capability — scripts can install/uninstall software, change system settings, access files, and reboot the machine.

API Tools

| Tool | Purpose | |------|---------| | immybot_scripts_list | List scripts with category/language/status filters | | immybot_scripts_get | Full detail for one script by ID | | immybot_scripts_search | Search scripts by name | | immybot_scripts_categories | List available script categories | | immybot_scripts_validate | Validate script syntax before running | | immybot_scripts_run | Execute a script on a computer (DESTRUCTIVE) | | immybot_scripts_execution_history | Past executions for a computer | | immybot_scripts_execution_result | Result of one specific execution |

Canonical Workflow

1. Find the script

immybot_scripts_search → immybot_scripts_get

Read the script description and confirm it matches the intended outcome. Prefer global, vetted scripts over ad-hoc ones.

2. Validate syntax (for new or modified scripts)

immybot_scripts_validate checks PowerShell syntax without executing anything. Always validate custom script content first.

3. Confirm the target

immybot_computers_get — confirm the computer is online and is the correct endpoint. Running a script on the wrong machine is the most common and most damaging mistake.

4. Get human approval

immybot_scripts_run is destructive. The MCP server returns a confirmation warning describing SYSTEM-context risk. Surface that warning, name the script and target computer explicitly, and obtain operator approval before proceeding.

5. Execute and capture

Call immybot_scripts_run with the script ID, target computer ID, optional parameters, timeout (default 30 min), and execution context (default System).

6. Review the result

immybot_scripts_execution_result   # this run
immybot_scripts_execution_history  # the computer's run history

Parameters & Timeouts

  • Parameters — passed as a parameter object; confirm required

parameters from immybot_scripts_get before running.

  • Timeout — default 30 minutes. Long-running remediation (large

installs, disk operations) may need a higher value.

  • Execution context — defaults to System. Only change this if

the script explicitly needs a user context.

Safety Rules

  • Never run a script without explicit human confirmation.
  • Always name the exact script and exact computer in the

approval request.

  • Validate custom script content with immybot_scripts_validate

before it ever runs.

  • For fleet-wide remediation, pilot on one endpoint and review the

execution result before expanding scope.

  • Log the approver, script ID, target, and outcome for every run.

Related Skills

  • [endpoint-management](../endpoint-management/SKILL.md) — pick and verify the target computer
  • [api-patterns](../api-patterns/SKILL.md) — destructive-operation confirmation pattern
Compartilhar X LinkedIn