---
title: "Docker destructive guardrails: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/skills/docker-docker-destructive-guardrails/
description: "States what a destructive Docker command will remove and waits for an explicit yes, except one narrow container cleanup."
---

# Docker destructive guardrails: review, setup & limitations · Undominated.ai

> States what a destructive Docker command will remove and waits for an explicit yes, except one narrow container cleanup.

[← Explore all skills](/skills/)

SAFETY / Docker

# Docker destructive guardrails

States what a destructive Docker command will remove and waits for an explicit yes, except one narrow container cleanup.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/docker/skills/tree/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-destructive-guardrails)

SOURCE REVIEW

 Reviewed 2026-10-15
 Evidence 4 linked sources
 Publisher Docker
 Licence [Apache-2.0 ↗](https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/LICENSE)
 Revision f79172733725
 [Read what was—and wasn’t—checked ↓](#review)

“Use this skill before running, or recommending, any Docker command that deletes, wipes, resets, or otherwise irreversibly changes state — even if the user just says to "clean up", "clear the cache", "start fresh", "wipe everything", "nuke it", "reset", "force remove", or "tear down" Docker resources. Covers generic Docker CLI destructive operations not owned by a more specific skill — `docker rm`, `docker rm -f`, `docker container prune`, `docker kill`, `docker system prune`, `docker rmi`/`docker image rm`, `docker image prune -a`, `docker network rm`, `docker network prune`, `docker builder prune`, `docker buildx rm`, `docker context rm`, and standalone (non-Compose) `docker volume rm`/`docker volume prune`. Also indexes destructive commands owned by other Docker skills (Compose, sandbox, Desktop). Core rule — state exactly what will be lost and get explicit confirmation first, except narrow, low-friction Tier 1 container cleanup.”

 [Docker · upstream description ↗](https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-destructive-guardrails/SKILL.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - Prune, kill, image, network, builder, context, and standalone volume deletes stay on the confirmation rule, including when the request is only to clean up.
- Tier 1 is only docker rm of one already-stopped container, or docker rm -f of one container this session created for a test, and only on an explicit ask. docker stop is reversible and still loses unsaved process state.

### A good fit for

 - Deciding whether a Docker cleanup command may run
- Keeping a disk-space or stuck-container fix narrower than a host-wide prune
- Distinguish disposable session-created containers from existing user workloads before cleanup.

### Weigh up before choosing

 - Docker stop interrupts a process but does not remove its container; the skill treats it separately from removal tiers.
- Desktop and sbx lifecycle behavior are delegated; this entry does not claim their full command coverage.
- The flag reference retains partly unverified docker rmi -f behavior; the cross-skill index was not re-reviewed.
- Installing the skill does not authorize deleting any existing Docker resource.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - skills/docker-destructive-guardrails/SKILL.md
- LICENSE
- skills/docker-destructive-guardrails/references/docker-cli-destructive-commands.md

### Our findings

 - The Apache appendix at this commit says Copyright 2026 Docker, Inc. There is no SPDX-License-Identifier line.
- docker context rm -f forces removal of a context that is in use. docker network rm -f is not described the same way. The skill says to read the reference for that difference.
- Pinned source distinguishes system prune --volumes anonymous-volume behavior from volume prune --all named-volume scope.
- It provides per-command alternatives rather than treating every force flag as equivalent.

### Not established by this review

 - No Docker command was run; image force-removal semantics were not independently runtime-tested.
- Not executed: it was not installed or run.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Add a skill to your workflow.

[Upstream setup instructions ↗](https://github.com/vercel-labs/skills/blob/48dc9e8eb8aa19040e91cb90ba0b642c9cbad57e/README.md)

DOCUMENTED COMMAND

 npx skills add docker/skills/skills/docker-destructive-guardrails Copy command ↗

Run in your terminal to choose your AI tools, project or global scope, and installation method. This short command follows the current upstream version; the review covers the revision shown above.

 Optional: install the reviewed revision

Keeps the original source and installer version where recorded, while leaving your AI tools and installation scope for you to choose.

 npx skills add https://github.com/docker/skills/tree/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-destructive-guardrails Copy reviewed-revision command ↗ - The command pins only this guardrail at the reviewed commit. The installer was not executed.
- Do not point the installer at the repository root if you only want this skill.

### Before you start

 - Node.js and npm
- A Docker CLI whose destructive commands you want gated

### Compatibility

Agent Skills hosts · Docker CLI

### Implementation

Markdown

### Policy text. It does not itself delete resources.

 - Read the command that is about to run
- The file does not grant docker rm, prune, or volume deletion
- Cleanup can delete data or shared build cache; broad prune and standalone volume removal require explicit scoped authorization.

### Cost model

Apache-2.0 instructions at no charge. Copyright 2026 Docker, Inc.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Skill definition ↗](https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-destructive-guardrails/SKILL.md) Checked 2026-10-14 https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-destructive-guardrails/SKILL.md Supports: summary, whySelected, limitations
- [Apache-2.0 licence ↗](https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/LICENSE) Checked 2026-10-07 https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/LICENSE Supports: Redistribution terms, Copyright 2026 Docker, Inc.
- [Per-command destructive flags reference ↗](https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-destructive-guardrails/references/docker-cli-destructive-commands.md) Checked 2026-10-14 https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-destructive-guardrails/references/docker-cli-destructive-commands.md Supports: review, limitations, access
- [2026-10-15 C2-W25 source re-review at the existing pin ↗](https://raw.githubusercontent.com/docker/skills/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-destructive-guardrails/SKILL.md) Checked 2026-10-15 https://raw.githubusercontent.com/docker/skills/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-destructive-guardrails/SKILL.md Supports: upstreamDescription, review.notTested, review.reviewedAt

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Docker Agent run ↗ Pins Docker's skill for docker agent run, including the safety modes and the exception that a local stdio MCP server stays outside the sandbox VM.](/skills/docker-agent-run/)[### Infisical User Setup Guide ↗ Infisical skill for getting secrets from Infisical into applications and platforms: the CLI, Docker, CI/CD, Kubernetes, the language SDKs and machine identity authentication.](/skills/infisical-setup/)[### Cloudflare cf CLI ↗ Pins Cloudflare's cf CLI skill, which tells an agent to search the local command index and to keep Wrangler when a Wrangler config is already present.](/skills/cloudflare-cf-cli/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Choose a toolkit](/tools/)
- [Inspect execution hosts](/agents/)
- [Check tool access](/mcp-servers/)
- [Check project dependencies](/check-repo/)
