Lateral Movement Readiness logo

Lateral Movement Readiness

Organization
zero-lab-ai
lateral-movement-readiness

Reviews an already-supplied lateral movement candidate for exact upstream map binding, authorization, non-production isolation, containment, telemetry, stop control, rollback, cleanup ownership, custody, tool governance, and a separate-validation handoff. Use before transferring a candidate to a lab validation team.

Overview

Publisherzero-lab-ai
Repositoryskills
Skill namelateral-movement-readiness
Stars
232
Forks
14
Bundled files
2
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by zero-lab-ai on GitHub. Read the source before you install it.

Installation

Install the Lateral Movement Readiness AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/zero-lab-ai/skills/tree/main/plugins/identity-security/skills/lateral-movement-readiness
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zero-lab-ai/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/plugins/identity-security/skills/lateral-movement-readiness .claude/skills/lateral-movement-readiness
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lateral Movement Readiness in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Lateral Movement Readiness on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Lateral Movement Readiness is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Lateral movement readiness

This skill answers one narrow question: may an already-supplied movement candidate be handed to a separate validation team? It checks records; it does not grant execution authority.

Never create, select, rank, enrich, or modify a movement candidate. Never produce commands, credentials, payloads, protocols, target locators, evasion, deployment, execution steps, or infrastructure. Accept only opaque identifiers and digests from the supplied record.

When to Use

  • Review lateral movement readiness for authorized security work.
  • Use only within explicit authorization and the stated rules of engagement.

When NOT to Use

  • Do not treat this skill as permission to access, test, or change a target.
  • Do not convert missing evidence into a clean result or a stronger claim.

Workflow

  1. Set one engagement assessment time and window. Record the governing policy and every supplied movement; the review treats all of them as the denominator.
  2. Bind each movement to the exact upstream map identifier and digest, scope, source, destination, policy, and environment. A digest or reference change is a different candidate, not a harmless edit.
  3. Accept only isolated-lab or dedicated-non-production environments. A production, shared, ambiguous, or merely named “test” environment is not eligible.
  4. Record bounded separate-validation authority. Bind it to the complete movement tuple and assessment window. Revocation and expiry take effect immediately.
  5. Cite independent evidence for map receipt, environment assurance, containment, telemetry, stop pretest, rollback, cleanup readiness, custody, and tool governance. Evidence must be current, eligible, and exactly bound.
  6. Assign cleanup ownership before readiness. A plan without an accountable owner remains blocked.
  7. Record one coverage cell for every movement and required role. Missing cells cannot become implicit non-applicability.
  8. Record a handoff only after exact approval and record receipts. Map drift, expiry, revocation, or a fired stop makes an existing handoff withdrawal-required. Resumption needs a new review; it is never automatic.
  9. For withdrawal, cite a later exact withdrawal receipt. Preserve the prior record and chronology.
  10. Complete the assessment and resolve every finding without altering the supplied movement identity.

Decision rules

  • prohibited overrides every other state.
  • approval-required means the bounded authority is absent, expired, or not yet effective; it does not mean “almost approved.”
  • blocked means a non-authority prerequisite is absent, stale, failed, or contradictory, including a fired stop.
  • ready-for-separate-validation requires every exact join and current receipt.
  • A recorded handoff is historical fact. It becomes withdrawal-required when its supporting state ceases to be current, and withdrawn only after proof.
  • “Not applicable” needs a documented reason; convenience is not evidence.

Report

Return the candidate ID, derived gate and validity, blocking codes, coverage counts, handoff state, and the next governance action. Keep all identifiers opaque. Do not quote restricted input in diagnostics or narrative.

Boundary

  • Use lateral-movement-map to construct or revise the upstream map.
  • Use a separate validation skill or authorized operator for any execution.
  • Send environment construction, telemetry configuration, or rollback implementation back to their accountable owners.
  • Treat a complete record as record consistency only, never authenticity, environment safety, operator competence, or execution authorization.

Rationalizations to reject

  • “It is only a lab.” Labels do not prove production separation or containment.
  • “The map is close enough.” A changed digest, source, destination, or scope invalidates the reviewed identity.
  • “The approval covers the general technique.” Authority is exact to the candidate, environment, bindings, action, and time window.
  • “Telemetry can be checked during the run.” Separate validation begins only after current observability assurance exists.
  • “A stop plan is enough.” The stop control needs independent, current, correctly bound pretest evidence; firing it invalidates readiness.
  • “Cleanup belongs to whoever runs it.” Ownership and rollback evidence are prerequisites, not post-run paperwork.
  • “The old handoff resumes when the issue clears.” Withdrawal and a fresh review are required; no auto-resume exists.
  • “PASS means approved.” The review proves only internal consistency of supplied facts.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Lateral Movement Readiness AI skill do?

Reviews an already-supplied lateral movement candidate for exact upstream map binding, authorization, non-production isolation, containment, telemetry, stop control, rollback, cleanup ownership, custody, tool governance, and a separate-validation handoff. Use before transferring a candidate to a lab validation team.

Why use Lateral Movement Readiness on TypingMind?

Because you install it once and use it with any model. Lateral Movement Readiness is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Lateral Movement Readiness in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zero-lab-ai/skills/tree/main/plugins/identity-security/skills/lateral-movement-readiness. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Lateral Movement Readiness?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Lateral Movement Readiness?

As many as you like. As long as a model supports skills, you can use Lateral Movement Readiness with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Lateral Movement Readiness AI skill free?

Yes. It is published on GitHub by zero-lab-ai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇