Engagement Manager logo

Engagement Manager

Community
brucesongs
engagement-manager

End-to-end penetration test project management skill. Orchestrates the full engagement lifecycle from scoping through reporting, managing skill composition, evidence chains, and phase transitions.

Overview

Publisherbrucesongs
Repositorykali-claw
Skill nameengagement-manager
Stars
70
Forks
18
Bundled files
12
LicenseMIT
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.

  • 12 bundled files

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

  • Open source

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

Installation

Install the Engagement Manager 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/brucesongs/kali-claw.git /tmp/kali-claw
mkdir -p .claude/skills
cp -r /tmp/kali-claw/skills/engagement-manager .claude/skills/engagement-manager
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Engagement Manager 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 Engagement Manager 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 Engagement Manager 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.

Engagement Manager

Summary

Orchestrates the full engagement lifecycle from scoping through reporting, managing skill composition, evidence chains, phase transitions, and stakeholder communication. Serves as the command center that coordinates specialized security skills, enforces scope boundaries, tracks progress across kill chain phases, and ensures deliverables meet professional standards.

Domain: management

Description

Engagement Manager is the orchestration skill that manages the full penetration testing lifecycle from initial scoping through final report delivery. It coordinates skill composition across 69 security domains, manages the kill chain phase progression (recon, scan, enum, vuln, exploit, post-exp), maintains evidence chain integrity, and ensures data handoffs between phases are complete and structured. The skill handles scope boundary enforcement, critical finding notification protocols, multi-target coordination, checkpoint-based pause/resume, and standardized report generation. It serves as the command center that activates specialized skills based on target type and manages the overall engagement state.

The engagement lifecycle follows a strict progression: Rules of Engagement (RoE) review and scope definition, target enumeration and attack surface mapping, systematic vulnerability discovery, controlled exploitation with evidence capture, post-exploitation assessment, and comprehensive reporting with remediation guidance. Each phase has entry criteria, exit criteria, and required evidence artifacts. The Engagement Manager ensures no phase is skipped, all data handoffs are validated, and findings are traceable from initial detection through final report inclusion.

Critical finding management is a key responsibility. When a high-severity vulnerability is confirmed (e.g., remote code execution, credential compromise, data exposure), the Engagement Manager triggers the notification protocol within the agreed timeframe (typically 4 hours), documents the finding with full evidence, and coordinates with the client for emergency remediation without disrupting the broader engagement. Multi-target engagements require careful parallel coordination — different skills may be active simultaneously against different targets, and the Engagement Manager must track all active threads, maintain separate evidence chains per target, and prevent scope confusion.

Use Cases

  • Manage a complete penetration test engagement from kickoff to report delivery with full phase tracking
  • Automatically select and sequence skills based on target type using the skill composition matrix
  • Track kill chain phase progress and data handoffs between phases with checkpoint validation
  • Maintain evidence chain integrity across multi-skill attack scenarios with checksums and timestamps
  • Generate standardized reports from collected evidence with executive summary and technical findings
  • Coordinate multi-target engagements with parallel skill activation and separate evidence chains
  • Enforce scope boundaries with zero violations; halt and document any scope boundary encounters
  • Handle critical finding notification within the agreed-upon timeframe while maintaining engagement continuity
  • Support engagement pause/resume with checkpoint-based state management for multi-day assessments
  • Conduct post-engagement quality assurance: evidence completeness, finding validation, report accuracy

Core Tools

ToolCategoryPurposeKey Command
orchestrator.shEngagement OrchestrationEnd-to-end penetration test workflow executionorchestrator.sh --target web --phase all
tool-selector.shTool SelectionTarget-to-tool mapping by attack phase and typetool-selector.sh --target-type web --phase recon
report-generator.shReportingAutomated report generation from collected evidencereport-generator.sh --source evidence/ --format html
drift-detect.shQuality AssuranceConfiguration drift detection and baseline managementdrift-detect.sh --create-baseline

Methodology

  1. Scope & Plan — Define target, scope rules, and skill chain based on target type. Review Rules of Engagement, identify in-scope and out-of-scope assets, establish communication channels and notification thresholds.
  2. Execute Kill Chain — Progress through recon, scan, enum, vuln, exploit, and post-exp phases with structured data handoff between each phase. Each phase has defined entry/exit criteria and required output artifacts.
  3. Evidence Collection — Capture structured evidence at each phase with timestamps, checksums, and tool command documentation. All evidence files follow a consistent naming convention and directory structure.
  4. Cross-Phase Validation — Verify findings from one phase inform the next. Reconnaissance results feed scanning targets, scan results drive enumeration focus, enumeration output identifies vulnerabilities for exploitation.
  5. Critical Finding Management — When high-severity findings are confirmed, trigger notification protocol within agreed timeframe, document with full evidence chain, and coordinate emergency remediation.
  6. Report Generation — Compile findings into standardized report with executive summary, technical findings, CVSS scores, remediation priorities, and evidence references.

Skill Composition

Target TypeSkills Activated
webweb-xss, web-sqli, web-auth-bypass, web-access-control, web-ssrf
cloudcloud-security, container-security, api-security, supply-chain-security
networknetwork-pentest, password-attack, post-exploitation
mobilemobile-security, binary-reverse
apiapi-security, web-auth-bypass, web-access-control

Key Decisions

  • IF target has web services → activate web-xss + web-sqli + web-auth-bypass
  • IF target is cloud-hosted → activate cloud-security + container-security
  • IF engagement duration < 8 hours → prioritize high-value attack paths
  • IF critical finding confirmed → pause, notify client within 4 hours
  • IF scope boundary hit → stop, document, request scope expansion

Practical Steps

  1. Initialize engagement — Create workspace directory structure, load target configuration (targets.json), define scope rules, and verify tool availability
  2. Determine skill composition — Map target type to appropriate security skills using the Skill Composition table
  3. Execute kill chain phases — Progress sequentially through recon, scan, enum, vuln, exploit, and post-exp phases, capturing structured evidence at each step
  4. Manage data handoffs — Ensure output from each phase feeds correctly into the next phase through standardized file formats
  5. Enforce scope boundaries — Continuously verify all targets and techniques remain within approved scope; halt and document any scope violations
  6. Handle critical findings — When critical vulnerabilities are discovered, follow the 4-hour notification protocol and document in evidence
  7. Track engagement state — Update checkpoint.json after each phase completion to enable pause/resume capability
  8. Generate report — Compile all evidence into a standardized report with executive summary, technical findings, CVSS scores, and remediation priorities
  9. Perform quality assurance — Validate evidence completeness, verify findings have all required fields, check report for placeholder text

Defense Perspective

Understanding the engagement lifecycle from a defensive perspective helps organizations prepare for and respond to penetration tests effectively:

  • Engagement indicators: Defenders should receive advance notice of authorized testing windows and source IP ranges to distinguish legitimate tests from actual attacks. A well-defined notification process prevents unnecessary incident response mobilization during authorized testing.
  • Detection during testing: Security teams should monitor for engagement artifacts — nmap scans, brute-force attempts, exploitation payloads — and verify these align with authorized testing schedules. This also tests the blue team's detection capabilities in real time.
  • Scope enforcement verification: Blue teams should independently verify that testing stays within approved scope by monitoring network traffic and log entries for activity against out-of-scope systems. Scope violations by testers indicate either a process failure or a genuine attack masquerading as authorized testing.
  • Evidence handling: Organizations should retain copies of all penetration test evidence for their own records and ensure the engagement team follows proper data handling procedures. Evidence should be encrypted at rest and securely destroyed after the retention period expires.
  • Post-engagement review: After testing concludes, defenders should conduct a lessons-learned session to identify detection gaps, response time improvements, and architectural weaknesses revealed by the test. This review should produce actionable items with owners and deadlines.
  • Purple team coordination: Engagement managers can structure purple team exercises where offensive actions are communicated to defenders in near-real-time, enabling calibration of detection rules and response procedures against actual attack techniques.
  • Remediation tracking: Post-engagement, the findings report becomes a remediation backlog. Organizations should track remediation progress, re-test critical findings, and update security controls based on lessons learned.

Phase Entry/Exit Criteria

PhaseEntry CriteriaExit CriteriaRequired Artifacts
ReconRoE reviewed, targets.json loadedAll in-scope assets enumeratedrecon-results.json, attack-surface.md
ScanRecon complete, target list validatedAll ports/services identifiedscan-results.xml, service-map.json
EnumScan complete, services cataloguedAll enumerated users/shares/configsenum-results.json, credential-stash.json
VulnEnum complete, attack surface mappedAll vulnerabilities classifiedvuln-results.json, risk-matrix.md
ExploitVuln confirmed, PoC validatedExploitation complete with evidenceexploit-evidence.json, screenshots/
Post-ExpExploitation successfulPost-exploitation objectives metpost-exp-results.json, lateral-map.json
ReportAll phases completeReport reviewed and deliveredfinal-report.pdf, evidence-archive.tar.gz

Evidence Requirements

Every finding must include these evidence artifacts for the engagement report to meet professional standards:

Evidence TypeRequired ForFormatNaming Convention
ScreenshotAll web findingsPNG with annotationsF-NNN-description.png
HTTP Request/ResponseWeb vulnerabilitiesRaw text or HARF-NNN-http-exchange.txt
Tool OutputAll automated findingsRaw with contextF-NNN-tool-output.txt
Console LogTerminal-based findingsCopy of session outputF-NNN-console.log
Packet CaptureNetwork-level findingsPCAP with filterF-NNN-capture.pcap
Video RecordingMulti-step exploitsMP4/GIFF-NNN-demo.mp4

Engagement Timeline Template

Day 1: Kickoff, RoE review, recon phase (passive + active)
Day 2: Port scanning, service enumeration, vulnerability scanning
Day 3: Manual testing, exploitation of confirmed vulnerabilities
Day 4: Post-exploitation, lateral movement, privilege escalation
Day 5: Evidence consolidation, report drafting, quality assurance
Day 6: Report review, client walkthrough, remediation planning

Adjust timeline based on scope: single-target web app (2-3 days), multi-target enterprise (10-15 days), continuous assessment (ongoing).

Communication Templates

TriggerTemplateRecipientTimeframe
Engagement kickoffkickoff-notification.mdClient SOC, IT lead24h before start
Critical findingcritical-finding-alert.mdClient security teamWithin 4 hours
Scope clarificationscope-change-request.mdClient sponsorBefore proceeding
Daily statusdaily-status-update.mdClient stakeholdersEnd of business day
Engagement completewrap-up-notification.mdClient SOC, IT leadWithin 24h of completion
Report deliveryreport-delivery-notice.mdClient sponsor, security teamPer contract schedule

Risk Assessment Matrix

Risk LevelCVSS RangeResponse TimeClient Notification
Critical9.0-10.0ImmediatePhone call within 2 hours
High7.0-8.9Within 24 hoursEmail within 4 hours
Medium4.0-6.9Within engagementIncluded in daily status
Low0.1-3.9In reportIncluded in final report
Informational0.0In reportIncluded in final report

Post-Engagement Checklist

  • All evidence files organized and integrity-verified (SHA256 checksums)
  • All findings have severity, CVSS score, PoC, impact, and remediation
  • Critical findings were notified within agreed timeframe
  • Scope boundaries verified — no unauthorized testing occurred
  • Temporary files, credentials, and test data cleaned up
  • Report follows template with executive summary and technical findings
  • Raw tool outputs archived for re-test reference
  • Client debrief scheduled for report walkthrough
  • Remediation priorities communicated with timeline recommendations
  • Engagement retrospective conducted — lessons learned documented

Detection Methods

Engagement Process Audit

  • Scope violations: Tester accessing systems outside engagement letter.
  • Time window violations: Activity outside authorized hours.
  • Data handling violations: Exfiltrating data without proper handling.

SIEM Detection Rules

  • Splunk SPL: Correlate tester activity with engagement scope document.
  • Custom workflow: Jira integration for engagement tracking.

Defense Evasion Techniques

Operational Security

  • Stay in scope: Don't access systems outside engagement letter; preserves legal protection.
  • Document everything: Maintain detailed audit trail; demonstrates authorization.
  • Time-boxed operations: Operate only during authorized hours.
  • Notify client: Pre-authorized activity reports; reduces incident response confusion.

Red Team / Blue Team Coordination

  • De-confliction channels: Establish communication with blue team; abort if detected.
  • Rules of engagement: Define stop conditions in advance.

Quality Criteria

  • All phases produce structured evidence files with timestamps
  • Data handoffs between phases are documented and verified
  • Findings include severity, CVSS score, PoC, impact, and remediation
  • Report follows standard penetration test template with all required sections
  • Evidence chain is complete, timestamped, and integrity-verified with checksums
  • Critical findings are notified within the agreed-upon timeframe
  • Scope boundaries are enforced with zero violations

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 Engagement Manager AI skill do?

End-to-end penetration test project management skill. Orchestrates the full engagement lifecycle from scoping through reporting, managing skill composition, evidence chains, and phase transitions.

Why use Engagement Manager on TypingMind?

Because you install it once and use it with any model. Engagement Manager 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 Engagement Manager in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/brucesongs/kali-claw/tree/main/skills/engagement-manager. 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 Engagement Manager?

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 Engagement Manager?

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

Is the Engagement Manager AI skill free?

Yes. It is published on GitHub by brucesongs under the MIT 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 👇