Rootkit Triage logo

Rootkit Triage

Organization
zero-lab-ai
rootkit-triage

Triages suspected rootkits, bootkits, hidden processes, kernel hooks, driver or module anomalies, concealed network activity, eBPF implants, and boot-integrity failures. Use when host tools may be lying and the incident needs evidence-preserving cross-view analysis, containment, or forensic handoff.

Overview

Publisherzero-lab-ai
Repositoryskills
Skill namerootkit-triage
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 Rootkit Triage 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/binary-forensics/skills/rootkit-triage
  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/binary-forensics/skills/rootkit-triage .claude/skills/rootkit-triage
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Rootkit Triage 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 Rootkit Triage 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 Rootkit Triage 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.

Rootkit triage

A suspected rootkit changes the reliability of the instrument used to inspect it. Treat live host output as one view, preserve provenance, and seek evidence from a different or lower trust layer before strengthening the claim.

This skill decides whether rootkit suspicion is unsupported, suspected, corroborated, or confirmed; what to preserve; and what containment or specialist handoff is justified. It does not perform full memory reconstruction, develop or deploy a rootkit, or prescribe live deletion from a system whose kernel or boot chain may be compromised.

When to Use

  • Host tools may be lying and the incident needs evidence-preserving cross-view analysis, containment, or forensic handoff.
  • 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. Record the asset, platform, authorization, business context, current isolation state, and suspected layers: userland, kernel, eBPF or driver, boot, hypervisor, or firmware.
  2. Inventory supplied evidence with its source, locator, acquisition time or bounded window, vantage, role, and integrity hash where the evidence record requires one. Do not invent acquisition precision.
  3. Assign trust from vantage rather than tool reputation. Live OS output is low trust for rootkit absence; external network observations and offline disk are medium; offline memory, hardware attestation, and external firmware reads are high.
  4. Compare independent views of processes, files, network activity, modules or drivers, hooks, eBPF state, boot measurements, firmware, and timing. Two tools that depend on the same live kernel do not form an independent cross-view.
  5. Build hypotheses from evidence and comparisons. A discrepancy supports suspicion. Corroboration needs independent vantage groups. Confirmation needs a high-trust direct artifact, an independent supporting vantage, and a discrepancy tied to the claim.
  6. Cover case context, preservation, process, file, network, module or driver, control-flow hook, eBPF, boot, firmware or hypervisor, memory, and containment questions. Keep unavailable layers blocked rather than clean.
  7. Plan preservation before reboot, artifact removal, rebuild, or firmware changes. Record authorization and evidence impact on every action. A review pass is not permission to execute it.
  8. Choose containment from the evidence strength and business impact. Preserve volatile evidence when feasible, isolate confirmed or corroborated cases, and use trusted-media rebuild or hardware escalation when the affected trust layer makes live cleanup unreliable.
  9. Hand detailed memory reconstruction to a memory-forensics workflow. Hand firmware acquisition to a hardware or firmware workflow. Keep the triage record as the chain between the initial discrepancy and those analyses.

Interpretation rules

  • Agreement among live tools is weak evidence because they may share the same compromised API, kernel structure, or hook.
  • A cross-view discrepancy is an indicator. Benign races, collection timing, permissions, parsing, and normal updates remain alternative explanations.
  • A matching boot measurement is evidence about measured components and the referenced baseline. It does not clear unmeasured firmware or runtime state.
  • A memory image acquired through the suspected kernel can still be manipulated. Record the acquisition vantage and preserve that limitation.
  • A valid signature establishes signer and file integrity, not benign behavior.
  • If kernel, boot, hypervisor, or firmware compromise is confirmed, restoration from trusted media and re-attestation are usually more defensible than live artifact deletion.

Rationalizations to reject

  • "Every live tool agrees, so the host is clean." Shared dependence on the same compromised layer can make agreement systematic deception.
  • "A discrepancy proves a rootkit." Collection races, permissions, parsing, and legitimate changes must remain visible until independent evidence resolves them.
  • "The scanner named a rootkit family." Signature output is a lead until its matched artifact and provenance are preserved and examined.
  • "Reboot first and see if it goes away." Reboot destroys volatile evidence and can activate boot persistence or recovery behavior.
  • "We found the file, so delete it now." Live removal can destroy evidence, trigger defensive behavior, or leave the lower trust layer compromised.
  • "Secure Boot passed, so firmware is fine." Attestation covers the measured chain and baseline; it does not establish every firmware component is benign.

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 Rootkit Triage AI skill do?

Triages suspected rootkits, bootkits, hidden processes, kernel hooks, driver or module anomalies, concealed network activity, eBPF implants, and boot-integrity failures. Use when host tools may be lying and the incident needs evidence-preserving cross-view analysis, containment, or forensic handoff.

Why use Rootkit Triage on TypingMind?

Because you install it once and use it with any model. Rootkit Triage 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 Rootkit Triage in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zero-lab-ai/skills/tree/main/plugins/binary-forensics/skills/rootkit-triage. 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 Rootkit Triage?

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 Rootkit Triage?

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

Is the Rootkit Triage 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 👇