Respond Compromised Account logo

Respond Compromised Account

Community
dandye
respond-compromised-account

Respond to a potentially compromised user account. Use when impossible travel, credential stuffing, successful phishing, or suspicious activity indicates account compromise. Investigates activity, contains the account, removes persistence, and restores access.

Overview

Publisherdandye
Repositoryai-runbooks
Skill namerespond-compromised-account
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 Compromised Account 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-compromised-account .claude/skills/respond-compromised-account
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Respond Compromised Account 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 Compromised Account 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 Compromised Account 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.

Compromised User Account Response Skill

Structured workflow for responding to potentially compromised user accounts using the PICERL model.

Inputs

  • USER_ID - Username or email of the potentially compromised user
  • CASE_ID - SOAR case ID for documentation
  • ALERT_GROUP_IDENTIFIERS - Alert group identifiers from SOAR
  • (Optional) INITIAL_ALERT_DETAILS - Summary of triggering alert

Required Outputs

After completing each phase, you MUST report these outputs:

Identification Phase

OutputDescription
AFFECTED_ACCOUNTSUser accounts confirmed or suspected compromised
SUSPICIOUS_ACTIVITYSummary of anomalous activity detected
ACCESS_SCOPESystems/data the account had access to
COMPROMISE_LIKELIHOODAssessment level: Low, Medium, High, Confirmed

Containment Phase

OutputDescription
DISABLED_ACCOUNTSAccounts that were disabled
RESET_PASSWORDSAccounts with passwords reset
REVOKED_SESSIONSSessions terminated

Eradication Phase

OutputDescription
REMOVED_PERSISTENCEPersistence mechanisms removed (forwarding rules, OAuth apps, etc.)
CLEANED_ENDPOINTSAssociated endpoints verified clean

Recovery Phase

OutputDescription
RESTORED_ACCOUNTSAccounts re-enabled with new security controls
USER_NOTIFICATIONSUsers notified of incident and required actions

PICERL Phases

Phase 2: Identification

Step 2.1: Get Context

secops-soar.get_case_full_details(case_id=CASE_ID)

Use /check-duplicates.

Step 2.2: Gather Initial Context

SIEM entity lookup:

secops-mcp.lookup_entity(entity_value=USER_ID)

(If IDP tools available):

  • Account status
  • Recent logins
  • MFA configuration
  • Password last changed

Step 2.3: Analyze User Activity

Search SIEM for last 96 hours:

secops-mcp.search_security_events(
    text="All activity for USER_ID",
    hours_back=96
)

Look for:

  • Anomalous logins: Unusual locations, times, IPs, user agents
  • Suspicious commands: On associated endpoints
  • Sensitive access: Files, applications, databases
  • Lateral movement: Logins to other systems
  • Data exfiltration: Large transfers, unusual destinations
  • Account changes: MFA, recovery email, forwarding rules
  • OAuth grants: New application authorizations

Step 2.4: Check Related Cases

Use /find-relevant-case with [USER_ID].

Step 2.5: Assess Compromise Likelihood

LevelIndicators
LowSingle anomalous event, user confirms legitimate
MediumMultiple anomalies, unverified
HighClear malicious activity patterns
ConfirmedKnown credential theft, attacker actions visible

Document: COMPROMISE_LIKELIHOOD

Step 2.6: Document Identification

Use /document-in-case with findings and assessment.


Phase 3: Containment

Step 3.1: Confirm Containment Actions

Based on COMPROMISE_LIKELIHOOD, use /confirm-action:

High/Confirmed:

"Disable account [USER_ID] immediately?"

Medium:

"Reset password and terminate sessions for [USER_ID]?"

Low:

"Force MFA re-enrollment for [USER_ID]?"

Step 3.2: Execute Containment

(Requires Identity Provider tools)

Actions by severity:

  • Disable account: Immediate lockout
  • Reset password: Force change on next login
  • Terminate sessions: Invalidate all active sessions
  • Revoke tokens: OAuth and API tokens

Step 3.3: Verify Containment

Monitor for continued activity:

secops-mcp.search_security_events(
    text="Activity from USER_ID after containment",
    hours_back=1
)

Use /document-in-case with containment status.


Phase 4: Eradication

Step 4.1: Investigate Attacker Actions

Thoroughly review what the attacker did while in the account:

secops-mcp.search_security_events(
    text="All actions by USER_ID during compromise window",
    hours_back=96
)

Focus on:

  • Emails: Sent, received, forwarding rules created
  • Data access: Files downloaded, shared externally
  • Configuration: Account settings changed
  • OAuth apps: New authorizations
  • Lateral movement: Other systems accessed

Step 4.2: Check for Persistence

(Requires email/cloud platform tools)

Look for:

  • Email forwarding rules to external addresses
  • Delegate access grants
  • Malicious OAuth applications
  • Inbox rules that hide attacker activity
  • Recovery email/phone changes

Step 4.3: Remove Persistence

Delete/revoke all identified persistence:

  • Remove forwarding rules
  • Revoke OAuth apps
  • Remove delegate access
  • Reset recovery options

Step 4.4: Endpoint Investigation

If account accessed specific endpoints:

Trigger endpoint triage to check for:

  • Malware dropped
  • Persistence mechanisms
  • Credential caching

Use /document-in-case with eradication findings.


Phase 5: Recovery

Step 5.1: Ensure Threat Removed

Verify:

  • All persistence removed
  • Associated endpoints clean
  • No ongoing attacker access

Step 5.2: Secure Account

  • Strong password set
  • MFA properly configured (hardware key preferred)
  • Recovery options secured
  • Review account permissions

Step 5.3: Re-enable Account

(If disabled during containment)

Re-enable with:

  • Password change required on first login
  • MFA verification required

Step 5.4: Communicate with User

Inform the user:

  • What happened (appropriate level of detail)
  • Actions taken on their account
  • Steps they need to take
  • Warning signs to watch for
  • How to report suspicious activity

Step 5.5: Monitor Account

Enhanced monitoring for 30 days:

  • Watch for anomalous activity
  • Alert on unusual logins
  • Track sensitive data access

Use /document-in-case with recovery status.


Phase 6: Lessons Learned

Use /generate-report with:

  • Initial access vector (if determined)
  • Attacker actions during compromise
  • Data potentially exposed
  • Response timeline
  • Recommendations

Review:

  • How was compromise detected?
  • Was MFA bypassed? How?
  • What data was at risk?
  • What detections should be added/tuned?

Critical Warnings

  • DO NOT execute containment without analyst confirmation
  • DO NOT re-enable without checking for persistence
  • MUST document all findings in SOAR
  • ALWAYS check for forwarding rules and OAuth apps

Containment Decision Matrix

LikelihoodDisable AccountReset PasswordTerminate Sessions
Confirmed✅ Immediate
High✅ Recommended
MediumConsider
LowNoConsiderConsider

Common Persistence Mechanisms

MechanismWhere to Check
Email forwardingMail rules
Delegate accessMailbox permissions
OAuth appsConnected applications
Inbox rulesMail filters
Recovery optionsAccount settings
API tokensDeveloper settings

Frequently asked questions

What does the Respond Compromised Account AI skill do?

Respond to a potentially compromised user account. Use when impossible travel, credential stuffing, successful phishing, or suspicious activity indicates account compromise. Investigates activity, contains the account, removes persistence, and restores access.

Why use Respond Compromised Account on TypingMind?

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

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

Which AI models can use Respond Compromised Account?

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 Compromised Account?

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

Is the Respond Compromised Account 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 👇