Respond Phishing logo

Respond Phishing

Community
dandye
respond-phishing

Respond to a reported phishing email following PICERL methodology. Use when a phishing email is reported or detected. Analyzes artifacts, identifies recipients who clicked, contains malicious IOCs, and removes emails from mailboxes.

Overview

Publisherdandye
Repositoryai-runbooks
Skill namerespond-phishing
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 Phishing 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-phishing .claude/skills/respond-phishing
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Respond Phishing 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 Phishing 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 Phishing 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.

Phishing Incident Response Skill

Structured workflow for responding to reported phishing emails using the PICERL model.

Inputs

  • CASE_ID - SOAR case ID for the incident
  • ALERT_GROUP_IDENTIFIERS - Alert group identifiers from SOAR
  • REPORTED_EMAIL_ARTIFACTS - Information about the email:
    • Email headers
    • Email body
    • Attached files (hashes)
    • URLs in email
    • Recipient user ID(s)
    • Sender address/domain

Required Outputs

After completing each phase, you MUST report these outputs:

Identification Phase

OutputDescription
PHISHING_URLSURLs extracted from email body
PHISHING_IOCSConfirmed malicious indicators (URLs, domains, hashes)
AFFECTED_USERSAll users who received the email
CLICKED_USERSUsers who clicked/interacted with malicious content
PHISHING_CATEGORYType: credential phish, spear phishing, BEC, malware delivery

Containment Phase

OutputDescription
BLOCKED_IOCSIOCs blocked at email gateway/proxy/firewall
CONTAINED_USERSUser accounts with restrictions applied
ISOLATED_ENDPOINTSEndpoints isolated due to suspicious activity

Eradication Phase

OutputDescription
DELETED_EMAILSCount of malicious emails removed from mailboxes
QUARANTINED_EMAILSEmails moved to quarantine

Recovery Phase

OutputDescription
RESTORED_ACCOUNTSUser accounts restored to normal access
USER_NOTIFICATIONSUsers notified of incident and required actions

PICERL Phases

Phase 2: Identification

Step 2.1: Get Context & Check Duplicates

secops-soar.get_case_full_details(case_id=CASE_ID)

Use /check-duplicates.

Step 2.2: Analyze Email Artifacts

Extract from email:

  • All URLs → EXTRACTED_URLS
  • Sender domain/IP
  • Attachment hashes → EXTRACTED_HASHES
  • Reply-to addresses
  • Header anomalies (SPF/DKIM failures)

Step 2.3: Enrich Extracted IOCs

For each IOC (URLs, domains, IPs, hashes):

Use /enrich-ioc:

/enrich-ioc IOC_VALUE IOC_TYPE

Identify confirmed malicious IOCs → MALICIOUS_IOCs.

Step 2.4: Categorize Phishing Type

CategoryIndicators
Generic Credential PhishBroad targeting, brand impersonation (Microsoft, Google)
Spear PhishingPersonalized, targets specific individuals
WhalingTargets executives
BECWire transfer requests, no malicious links
Brand ImpersonationMimics known brands
Malware DeliveryFocus on attachments or download links

Document: PHISHING_CATEGORY

Step 2.5: Search for Related Activity (SIEM)

secops-mcp.search_security_events(
    text="Network connections or DNS to MALICIOUS_IOCs",
    hours_back=72
)

Look for:

  • Other emails with same subject/sender
  • URL clicks to malicious URLs
  • File executions of malicious hashes
  • Suspicious activity from recipients

Step 2.6: Identify Impact

  • SIMILAR_EMAIL_RECIPIENTS - Who else received it
  • POTENTIAL_COMPROMISED_USERS - Who clicked/interacted
  • SUSPICIOUS_ENDPOINTS - Endpoints with related activity

Step 2.7: Document Identification

Use /document-in-case with findings.


Phase 3: Containment

Step 3.1: Block Network IOCs

For each IOC in MALICIOUS_IOCs:

Use /confirm-action:

"Block domain/IP/URL [VALUE]?"

If confirmed, implement blocks at:

  • Email gateway
  • Web proxy
  • Firewall
  • DNS

Step 3.2: Contain Potentially Compromised Users

For each user in POTENTIAL_COMPROMISED_USERS:

Trigger /respond-compromised-account

Step 3.3: Isolate Suspicious Endpoints

For each endpoint in SUSPICIOUS_ENDPOINTS:

Use /confirm-action:

"Isolate endpoint [HOSTNAME]?"

Step 3.4: Verify Containment

Monitor for continued activity to blocked IOCs.

Use /document-in-case with containment status.


Phase 4: Eradication

Step 4.1: Delete Malicious Emails

(Requires Email Gateway/Platform tools)

Search all mailboxes for:

  • Same subject line
  • Same sender
  • Contains malicious URLs/attachments

Delete/quarantine identified emails. Document count of emails removed.

Step 4.2: Address Malware (If Applicable)

If phishing led to malware execution: → Trigger /respond-malware

Step 4.3: Document Eradication

Use /document-in-case with email deletion counts and actions.


Phase 5: Recovery

Step 5.1: User Account Recovery

If accounts disabled during containment:

  • Verify threat is removed
  • Re-enable accounts
  • Force password change if credentials potentially compromised

Step 5.2: Endpoint Recovery

If endpoints isolated:

  • Verify clean before reconnecting
  • Follow malware response recovery if infected

Step 5.3: Validate Countermeasures

After lifting blocks, verify legitimate traffic isn't blocked.

Step 5.4: User Communication

Notify affected users:

  • What happened
  • Actions taken
  • What they should do (change passwords, be vigilant)

Phase 6: Lessons Learned

Use /generate-report with:

  • Phishing category
  • Impact assessment
  • Response timeline
  • Emails deleted count
  • Recommendations

Conduct review:

  • How did it bypass email filters?
  • Detection effectiveness
  • User awareness gaps
  • Recommended filter/rule updates

Critical Warnings

  • DO check who else received the email
  • DO NOT leave malicious emails in mailboxes
  • DO NOT block legitimate business domains (verify first)
  • VERIFY extracted domains against company-owned domains list

Phishing Response Checklist

  • Email artifacts analyzed
  • IOCs enriched and categorized
  • All recipients identified
  • Click/interaction assessed
  • Malicious IOCs blocked
  • Compromised users contained
  • Malicious emails deleted from ALL mailboxes
  • Users notified
  • Report generated

Frequently asked questions

What does the Respond Phishing AI skill do?

Respond to a reported phishing email following PICERL methodology. Use when a phishing email is reported or detected. Analyzes artifacts, identifies recipients who clicked, contains malicious IOCs, and removes emails from mailboxes.

Why use Respond Phishing on TypingMind?

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

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

Which AI models can use Respond Phishing?

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 Phishing?

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

Is the Respond Phishing 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 👇