Respond Malware logo

Respond Malware

Community
dandye
respond-malware

Respond to a malware incident following PICERL methodology. Use when malware is detected on endpoints. Orchestrates triage, containment, eradication, and recovery. Works with triage-malware skill for analysis.

Overview

Publisherdandye
Repositoryai-runbooks
Skill namerespond-malware
Stars
126
Forks
34
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by dandye on GitHub. Read the source before you install it.

Installation

Install the Respond Malware 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.
  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/dandye/ai-runbooks.git /tmp/ai-runbooks
mkdir -p .claude/skills
cp -r /tmp/ai-runbooks/skills/respond-malware .claude/skills/respond-malware
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Respond Malware 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 Respond Malware 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 Respond Malware 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.

Malware Incident Response Skill

Structured workflow for responding to suspected malware incidents using the PICERL model.

Inputs

  • CASE_ID - SOAR case ID for the incident
  • ALERT_GROUP_IDENTIFIERS - Alert group identifiers from SOAR
  • INITIAL_INDICATORS - Details from initial alerts:
    • File hashes
    • IPs/domains
    • Affected hosts
    • Affected users

Required Outputs

After completing each phase, you MUST report these outputs:

Identification Phase

OutputDescription
AFFECTED_HOSTSHosts with confirmed malware
MALWARE_SAMPLESFile hashes requiring triage/analysis
MALWARE_IOCSNetwork indicators (IPs, domains, URLs)
AFFECTED_USERSUsers who executed/accessed malware

Containment Phase

OutputDescription
ISOLATED_HOSTSHosts successfully isolated from network
BLOCKED_IOCSIOCs blocked at firewall/proxy

Eradication Phase

OutputDescription
CLEANED_HOSTSHosts with malware removed
REMOVED_PERSISTENCEPersistence mechanisms removed

Recovery Phase

OutputDescription
RESTORED_HOSTSHosts restored to operational state
VALIDATION_STATUSPost-recovery scan results

PICERL Phases

Phase 2: Identification

Step 2.1: Initial Triage

Use /triage-alert with CASE_ID for initial assessment.

secops-soar.get_case_full_details(case_id=CASE_ID)

Use /check-duplicates.

Step 2.2: Malware Triage

If file hash is primary indicator:

Use /triage-malware:

/triage-malware FILE_HASH=abc123 CASE_ID=1234

This provides:

  • GTI classification
  • Behavioral indicators
  • Network IOCs
  • Affected hosts/users

Step 2.3: IOC Enrichment

For other key IOCs (IPs, domains, URLs):

Use /enrich-ioc for each.

Step 2.4: Initial Scope Assessment

Compile:

  • AFFECTED_ENDPOINTS - Hosts with malware
  • AFFECTED_USERS - Users who executed/accessed
  • MALICIOUS_IOCs - Network indicators

Use /document-in-case with findings.


Phase 3: Containment

Step 3.1: Endpoint Isolation

For each endpoint in AFFECTED_ENDPOINTS:

Use /confirm-action:

"Isolate endpoint [HOSTNAME] from network?"

If confirmed, execute isolation via EDR.

Step 3.2: Network IOC Containment

For each IOC in MALICIOUS_IOCs:

Use /confirm-action:

"Block [IOC_TYPE] [VALUE] at firewall/proxy?"

If confirmed, implement blocks.

Step 3.3: User Account Containment

If compromised user involved:

Trigger /respond-compromised-account

Step 3.4: Verify Containment

Monitor for continued activity:

secops-mcp.search_security_events(
    text="Activity from contained IOCs or endpoints",
    hours_back=1
)

Use /document-in-case with containment status.


Phase 4: Eradication

Step 4.1: Identify Persistence

From /triage-malware results and GTI behavior summary, identify:

  • Scheduled tasks
  • Services installed
  • Registry modifications
  • Dropped files
  • WMI subscriptions

Step 4.2: Remove Malware & Persistence

(Requires EDR/endpoint tools)

Execute removal plan:

  1. Terminate malicious processes
  2. Delete malware files
  3. Remove persistence mechanisms
  4. Clear malicious registry keys

Step 4.3: Scan for Residual Infection

(Requires EDR/AV tools)

Perform thorough scans post-eradication.

Use /document-in-case with eradication results.


Phase 5: Recovery

Step 5.1: Determine Recovery Strategy

Based on severity and admin rights involved:

FactorRebuildClean
Admin rights compromised
Unknown malware
Known commodity malwareConsider
High confidence eradicationConsider

Step 5.2: Execute Recovery

(Involves IT Ops/System Admins)

  • Rebuild from known-good image OR clean existing
  • Apply all patches before reconnecting
  • Perform vulnerability scan
  • Restore data from clean backups if needed

Step 5.3: Monitor Recovered Systems

Closely monitor for 24-72 hours post-recovery:

  • Watch for re-infection indicators
  • Monitor for unusual behavior
  • Verify normal operations

Step 5.4: Lift Containment

Gradually remove isolation once confidence is high.

Use /document-in-case with recovery status.


Phase 6: Lessons Learned

Use /generate-report with:

  • Malware classification
  • Entry vector
  • Spread/impact
  • Response timeline
  • Recovery actions
  • Recommendations

Conduct review:

  • How did malware enter?
  • Was detection timely?
  • Were containment actions effective?
  • What detections should be added?

Critical Warnings

  • DO NOT skip endpoint isolation for confirmed infections
  • MUST identify malware strain/behavior
  • DO NOT restore without verifying eradication
  • ALWAYS verify scan results before reconnecting

Malware Response Quick Reference

PhaseKey QuestionAction
IdentificationWhat is it?/triage-malware
IdentificationWhere is it?SIEM search
ContainmentStop the spreadIsolate endpoints
ContainmentBlock C2Block network IOCs
EradicationRemove itEDR remediation
RecoveryRestore opsRebuild or clean

Frequently asked questions

What does the Respond Malware AI skill do?

Respond to a malware incident following PICERL methodology. Use when malware is detected on endpoints. Orchestrates triage, containment, eradication, and recovery. Works with triage-malware skill for analysis.

Why use Respond Malware on TypingMind?

Because you install it once and use it with any model. Respond Malware 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 Respond Malware in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dandye/ai-runbooks/tree/main/skills/respond-malware. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Respond Malware?

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 Respond Malware?

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

Is the Respond Malware AI skill free?

Yes. It is published on GitHub by dandye 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 👇