Threat Hunting

Q: Why use Threat Hunting on TypingMind?

Because you install it once and use it with any model. Threat Hunting 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.

Q: How do I install Threat Hunting in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hypnguyen1209/offensive-claude/tree/main/skills/threat-hunting. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Q: Which AI models can use Threat Hunting?

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.

Q: How many AI models can I use with Threat Hunting?

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

Q: Is the Threat Hunting AI skill free?

Yes. It is published on GitHub by hypnguyen1209 under the MIT license. You only pay your own AI provider for the tokens you use.

Q: 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.

Q: 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.

Community

hypnguyen1209

threat-hunting

Use when hunting threats or engineering detections — ATT&CK Detection-Strategies, Sigma + correlation with Detection-as-Code CI, Windows endpoint hunting (Sysmon/ETW/LSASS/LOLBins), network C2 hunting (JA4+, beaconing, DNS tunneling), cloud-identity hunting, Atomic Red Team purple-team validation

Overview

Publisher	hypnguyen1209
Repository	`offensive-claude`
Skill name	`threat-hunting`
Stars	396
Forks	71
Bundled files	14
License	MIT
Links	Skill source Repository

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.
14 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by hypnguyen1209 on GitHub. Read the source before you install it.

Installation

Install the Threat Hunting AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/hypnguyen1209/offensive-claude/tree/main/skills/threat-hunting
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.

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/hypnguyen1209/offensive-claude.git /tmp/offensive-claude
mkdir -p .claude/skills
cp -r /tmp/offensive-claude/skills/threat-hunting .claude/skills/threat-hunting

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Threat Hunting 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 Threat Hunting 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 Threat Hunting 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.

Threat Hunting & Detection Engineering

When to Activate

Hypothesis-driven hunting across endpoint, network, cloud, and identity telemetry
Writing & shipping detections (Sigma + correlation) as version-controlled code in CI
Mapping & measuring coverage against MITRE ATT&CK v18 (Detection Strategies / Analytics)
Hunting Windows post-exploitation: ETW/AMSI tampering, LSASS dumping, LOLBins, injection
Hunting C2 in encrypted traffic: JA4+/JA4X fingerprints, beaconing, DNS tunneling
Hunting cloud-identity attacks: Entra device-code/OAuth phishing, PRT theft, CloudTrail abuse
Purple-team validation: emulate ATT&CK with Atomic Red Team/Caldera, find detection gaps
Triaging EVTX/Zeek/CloudTrail offline during IR without a SIEM

Technique Map

Technique	ATT&CK	CWE	Reference	Script
Hypothesis-driven hunt loop (PEAK/TaHiTI)	TA0043	CWE-778	references/methodology-hunt-loop.md	-
ATT&CK v18 Detection-Strategies / Analytics mapping	TA0043	CWE-778	references/methodology-hunt-loop.md	scripts/coverage_matrix.py
Detection-as-Code CI (lint + compile)	TA0043	CWE-778	references/methodology-hunt-loop.md	scripts/dac_validate.py
Sysmon 15 PPL + tamper/visibility-gap	T1562.001	CWE-693	references/windows-endpoint-hunting.md	scripts/sysmon_config_2025.xml
ETW / AMSI in-memory patch detection	T1562.001, T1562.002	CWE-693	references/windows-endpoint-hunting.md	scripts/evtx_hunt.py
LSASS credential-access handle hunt	T1003.001	CWE-522	references/windows-endpoint-hunting.md	scripts/evtx_hunt.py
LOLBin / process-tree anomaly hunt	T1218, T1105, T1059	CWE-78	references/windows-endpoint-hunting.md	scripts/evtx_hunt.py
Sigma rule + correlation engineering	TA0043	CWE-778	references/sigma-rule-engineering.md	scripts/dac_validate.py
EVTX triage (Hayabusa/Chainsaw/Velociraptor)	TA0043	CWE-778	references/sigma-rule-engineering.md	scripts/sigma_pipeline.sh
JA4+/JA4X C2 fingerprinting	T1071.001	CWE-300	references/network-c2-hunting.md	scripts/beacon_hunter.py
Beaconing / long-conn / prevalence (RITA-style)	T1071, T1571	CWE-940	references/network-c2-hunting.md	scripts/beacon_hunter.py
DNS tunneling / DGA / DoH abuse	T1071.004, T1572	CWE-940	references/network-c2-hunting.md	scripts/beacon_hunter.py
Entra device-code / OAuth consent phishing	T1528, T1566	CWE-287	references/cloud-identity-hunting.md	scripts/entra_hunt.kql
PRT theft / token replay	T1550.001	CWE-522	references/cloud-identity-hunting.md	scripts/entra_hunt.kql
AWS CloudTrail abuse / log tampering	T1078.004, T1098, T1562.008	CWE-269	references/cloud-identity-hunting.md	scripts/cloudtrail_hunt.py
Atomic Red Team / Caldera validation	TA0043	CWE-778	references/purple-team-validation.md	scripts/coverage_matrix.py
Coverage matrix + ATT&CK Navigator + gap report	TA0043	CWE-778	references/purple-team-validation.md	scripts/coverage_matrix.py

Quick Start

bash
# 0. Deploy hunting telemetry baseline (Sysmon 15+, PPL self-protected)
sysmon -accepteula -i scripts/sysmon_config_2025.xml      # or: sysmon -c <file> to update

# 1. Offline endpoint triage over collected EVTX (no SIEM)
python3 scripts/evtx_hunt.py /cases/host01/EVTX --min-severity medium --json host01.json

# 2. Network: hunt C2 beacons / DNS tunneling over Zeek logs (+ optional JA4 blocklist)
zeek -r capture.pcap LogAscii::use_json=T
python3 scripts/beacon_hunter.py --conn conn.log --dns dns.log \
        --ja4-blocklist bad_ja4.txt --min-score 0.7

# 3. Cloud/identity: paste scripts/entra_hunt.kql into Sentinel/Defender;
#    triage AWS offline:
python3 scripts/cloudtrail_hunt.py /cases/cloudtrail/ --json ct_findings.json

# 4. Detection-as-Code: lint + compile your Sigma repo for CI (fail-fast)
python3 scripts/dac_validate.py rules/ --backend splunk --pipeline sysmon --fail-on-error
./scripts/sigma_pipeline.sh rules/ build/ splunk microsoft365defender elasticsearch

# 5. Purple-team validate + measure coverage (ATT&CK v18 Navigator layer + gaps)
Invoke-AtomicTest T1003.001 -TestNumbers 1,2,3   # lab only; -Cleanup after
python3 scripts/coverage_matrix.py --rules rules/ --atomic-results atomic_results.json \
        --watchlist watchlist.txt --navigator-out attack_layer.json --gaps-out gaps.csv

OPSEC & Detection (summary)

Technique	Telemetry / IOC	Detection (Sigma / EDR)	OPSEC note
ETW/AMSI patch	RWX in ntdll/amsi; ScriptBlock w/ AmsiScanBuffer+VirtualProtect	Sigma AMSI/ETW patch rule; Sysmon EID 25; ETW-TI (kernel)	Userland patch defeats single source — correlate EID25 + ETW-TI + behavior
Sysmon kill	System 7036/7034, SysmonDrv unload, EPS drop to 0	Visibility-gap metric on chatty hosts	Sysmon 15 is PPL; attacker kills agent instead — alert on stop/unload
LSASS dump	EID 10 handle to lsass + `.dmp` write	LSASS-access Sigma; access-mask + non-system source	Baseline your own EDR/AV SourceImage set first or you flood the SOC
LOLBin abuse	certutil/mshta/regsvr32 + http/decode/scrobj	LOLBin Sigma; parent→child tree anomalies	Hunt cold data first; live triage tips an EDR-aware operator
Beaconing	periodic intervals, uniform sizes, low prevalence	beacon_hunter.py CV<0.3; RITA; long-conn on non-interactive port	Need days of logs — small PCAPs inflate FPs
JA4X C2	randomized certs sharing one JA4X (Sliver/Havoc)	JA4 segment-pivot; JA4X blocklist at TLS-terminating proxy	TLS 1.3 encrypts certs — capture at egress/proxy, don't block on FP alone
DNS tunneling	long/high-entropy subdomains, TXT volume, NXDOMAIN spikes	DNS entropy/volume scoring; DoH-to-public Sigma	Baseline normal long-FQDN apps (CDNs) before alerting
Device-code phish	`deviceCode` sign-in, broker/OfficeHome AppId, new ASN	entra_hunt.kql #1+#2; Elastic open rules	Baseline sanctioned device-code apps; not every device-code is evil
PRT theft	`primaryRefreshToken` from multi-geo same day	PRT KQL + LSASS/cloudAP endpoint join	Control-plane is the ONLY evidence — retain logs ≥90d before you need them
CloudTrail abuse	StopLogging/DeleteTrail, CreateAccessKey for others, Describe* burst	cloudtrail_hunt.py; Athena tamper query	Attackers disable logging early; enable org-wide all-region trail up front

Deep Dives

references/methodology-hunt-loop.md — PEAK/TaHiTI hunt loop, ATT&CK v18 Detection Strategies (DETxxxx) & Analytics (ANxxxx) replacing legacy data sources, Detection-as-Code CI/CD (PTEFv4), visibility-gap detection.
references/windows-endpoint-hunting.md — Sysmon 15 PPL & tamper detection, ETW/AMSI in-memory patch detection (ETW-TI, EID 25, ScriptBlock), LSASS handle hunting, LOLBins & process-tree anomalies.
references/sigma-rule-engineering.md — Sigma rule anatomy, correlation rules (value_count/temporal), pySigma/sigma-cli compile, Hayabusa/Chainsaw/Velociraptor 0.74 native-Sigma EVTX triage, AI-assisted authoring (SigmaGen/Uncoder).
references/network-c2-hunting.md — JA4+/JA4S/JA4H/JA4X fingerprinting, Sliver/Havoc shared JA4X, RITA-style beaconing & long-connection stats, DNS tunneling/DGA/DoH, C2 framework signature cheat-sheet.
references/cloud-identity-hunting.md — Entra device-code phishing (STORM-2372, Tycoon2FA, EvilTokens), OAuth consent abuse, PRT theft, Graph enumeration, AWS CloudTrail abuse & tampering.
references/purple-team-validation.md — Atomic Red Team unit tests, MITRE Caldera chained emulation, ATT&CK v18-aware coverage matrix, Navigator layer generation, prioritized gap analysis.

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 Threat Hunting AI skill do?

Why use Threat Hunting on TypingMind?

Because you install it once and use it with any model. Threat Hunting 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 Threat Hunting in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hypnguyen1209/offensive-claude/tree/main/skills/threat-hunting. 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 Threat Hunting?

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 Threat Hunting?

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

Is the Threat Hunting AI skill free?

Yes. It is published on GitHub by hypnguyen1209 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

Internal Comms

anthropics

OrganizationPopular

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal…

Claude Opus 4 5 Migration

anthropics

OrganizationPopular

Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string…

Deploy Release Test

Validate a commit-specific Next.js preview package and manually trigger the entire Next.js deployment test suite through the test_e2e_deploy_release.yml GitHub Actions workflow. Use only when asked to…

Insight Error Page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new `errors/<slug>.mdx` page, auditing an existing one, or checking that a page matches the framework fix…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Threat Hunting & Detection Engineering

When to Activate

Technique Map

Quick Start

OPSEC & Detection (summary)

Deep Dives

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now