agentleFS
hypnguyen1209hypnguyen1209/offensive-claude/skills/threat-hunting/SKILL.md

threat-hunting

Skill401 starsChanged 56 days agoMITView on GitHub

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

12 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use incident-triage and threat-modeling.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • testified-ossSkill

    incident-triage

    Triage production incidents with severity assessment, root cause hypothesis, impact analysis, and escalation recommendations. Use when analyzing outages, errors, or production issues.

    Also in 3 projects that use this

  • msewellSkill

    threat-modeling

    Produces structured threat models for software systems using STRIDE on data flow diagrams. Generates DFDs with trust boundaries, identifies threats per element, scores risks, and defines concrete mitigations. Outputs a complete threat model Markdown document through phased, interactive delivery. Use when threat modeling a system, analyzing security threats, identifying attack surfaces, performing STRIDE analysis, assessing security risks in architecture, creating a threat model document, or when the user mentions threat model, attack surface, trust boundaries, STRIDE, or security risk analysis.

    Also in 3 projects that use this

The file

Files
SKILL.md

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

TechniqueATT&CKCWEReferenceScript
Hypothesis-driven hunt loop (PEAK/TaHiTI)TA0043CWE-778references/methodology-hunt-loop.md-
ATT&CK v18 Detection-Strategies / Analytics mappingTA0043CWE-778references/methodology-hunt-loop.mdscripts/coverage_matrix.py
Detection-as-Code CI (lint + compile)TA0043CWE-778references/methodology-hunt-loop.mdscripts/dac_validate.py
Sysmon 15 PPL + tamper/visibility-gapT1562.001CWE-693references/windows-endpoint-hunting.mdscripts/sysmon_config_2025.xml
ETW / AMSI in-memory patch detectionT1562.001, T1562.002CWE-693references/windows-endpoint-hunting.mdscripts/evtx_hunt.py
LSASS credential-access handle huntT1003.001CWE-522references/windows-endpoint-hunting.mdscripts/evtx_hunt.py
LOLBin / process-tree anomaly huntT1218, T1105, T1059CWE-78references/windows-endpoint-hunting.mdscripts/evtx_hunt.py
Sigma rule + correlation engineeringTA0043CWE-778references/sigma-rule-engineering.mdscripts/dac_validate.py
EVTX triage (Hayabusa/Chainsaw/Velociraptor)TA0043CWE-778references/sigma-rule-engineering.mdscripts/sigma_pipeline.sh
JA4+/JA4X C2 fingerprintingT1071.001CWE-300references/network-c2-hunting.mdscripts/beacon_hunter.py
Beaconing / long-conn / prevalence (RITA-style)T1071, T1571CWE-940references/network-c2-hunting.mdscripts/beacon_hunter.py
DNS tunneling / DGA / DoH abuseT1071.004, T1572CWE-940references/network-c2-hunting.mdscripts/beacon_hunter.py
Entra device-code / OAuth consent phishingT1528, T1566CWE-287references/cloud-identity-hunting.mdscripts/entra_hunt.kql
PRT theft / token replayT1550.001CWE-522references/cloud-identity-hunting.mdscripts/entra_hunt.kql
AWS CloudTrail abuse / log tamperingT1078.004, T1098, T1562.008CWE-269references/cloud-identity-hunting.mdscripts/cloudtrail_hunt.py
Atomic Red Team / Caldera validationTA0043CWE-778references/purple-team-validation.mdscripts/coverage_matrix.py
Coverage matrix + ATT&CK Navigator + gap reportTA0043CWE-778references/purple-team-validation.mdscripts/coverage_matrix.py

Quick Start

# 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)

TechniqueTelemetry / IOCDetection (Sigma / EDR)OPSEC note
ETW/AMSI patchRWX in ntdll/amsi; ScriptBlock w/ AmsiScanBuffer+VirtualProtectSigma AMSI/ETW patch rule; Sysmon EID 25; ETW-TI (kernel)Userland patch defeats single source — correlate EID25 + ETW-TI + behavior
Sysmon killSystem 7036/7034, SysmonDrv unload, EPS drop to 0Visibility-gap metric on chatty hostsSysmon 15 is PPL; attacker kills agent instead — alert on stop/unload
LSASS dumpEID 10 handle to lsass + .dmp writeLSASS-access Sigma; access-mask + non-system sourceBaseline your own EDR/AV SourceImage set first or you flood the SOC
LOLBin abusecertutil/mshta/regsvr32 + http/decode/scrobjLOLBin Sigma; parent→child tree anomaliesHunt cold data first; live triage tips an EDR-aware operator
Beaconingperiodic intervals, uniform sizes, low prevalencebeacon_hunter.py CV<0.3; RITA; long-conn on non-interactive portNeed days of logs — small PCAPs inflate FPs
JA4X C2randomized certs sharing one JA4X (Sliver/Havoc)JA4 segment-pivot; JA4X blocklist at TLS-terminating proxyTLS 1.3 encrypts certs — capture at egress/proxy, don't block on FP alone
DNS tunnelinglong/high-entropy subdomains, TXT volume, NXDOMAIN spikesDNS entropy/volume scoring; DoH-to-public SigmaBaseline normal long-FQDN apps (CDNs) before alerting
Device-code phishdeviceCode sign-in, broker/OfficeHome AppId, new ASNentra_hunt.kql #1+#2; Elastic open rulesBaseline sanctioned device-code apps; not every device-code is evil
PRT theftprimaryRefreshToken from multi-geo same dayPRT KQL + LSASS/cloudAP endpoint joinControl-plane is the ONLY evidence — retain logs ≥90d before you need them
CloudTrail abuseStopLogging/DeleteTrail, CreateAccessKey for others, Describe* burstcloudtrail_hunt.py; Athena tamper queryAttackers 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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.