Threat Hunting

What it does

When your agent uses it

• Hunting threats
• Engineering detections — ATT&CK Detection-Strategies
• Sigma + correlation with Detection-as-Code CI
• Windows endpoint hunting (Sysmon/ETW/LSASS/LOLBins)

Example prompts

• “/threat-hunting”

Requirements

• Python 3
• A Bash shell

What it can do on your machine

Read from SKILL.md and the folder at commit a506ad3. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 8 files in scripts/ (Python and Shell), which the agent can run.

  Shell commands in SKILL.md call:

  • python3

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Threat Hunting loads about 2.4k tokens when it runs, and up to ~16k if it reads all its reference files. Until then it costs about 78 tokens; SKILL.md has 600 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~78

When it runs · the whole SKILL.md, loaded when a task matches

~2.4k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~16k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from hypnguyen1209/offensive-claude at commit a506ad3, republished under its MIT licence (© hypnguyen1209). 600 words, ~2,352 tokens.

name

threat-hunting

description

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

metadata.type

defensive

metadata.phase

detection

metadata.tools

sigma-cli, pysigma, hayabusa, chainsaw, velociraptor, sysmon, zeek, rita, ja4, atomic-red-team, caldera, splunk, sentinel, defender, kql

metadata.mitre

TA0043

kill_chain.phase

report

kill_chain.step

8

kill_chain.attck_tactics

TA0043, TA0042, TA0011, TA0006, TA0005

kill_chain.attck_techniques

T1059.001, T1003.001, T1562.001, T1562.002, T1218, T1105, T1071, T1071.001, T1071.004, T1571, T1572, T1528, T1550.001, T1078.004, T1098, T1543.003, T1070.001…

depends_on

red-team-ops, incident-response

inputs

finding_records, log_data, ioc_list, evtx, zeek_logs, cloudtrail, sigin_logs

# 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

© hypnguyen1209, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 14 other files (scripts, references) in skills/threat-hunting of hypnguyen1209/offensive-claude.

• SKILL.md
• references/cloud-identity-hunting.md
• references/methodology-hunt-loop.md
• references/network-c2-hunting.md
• references/purple-team-validation.md
• references/sigma-rule-engineering.md
• references/windows-endpoint-hunting.md
• scripts/beacon_hunter.py
• scripts/cloudtrail_hunt.py
• scripts/coverage_matrix.py
• scripts/dac_validate.py
• scripts/entra_hunt.kql
• scripts/evtx_hunt.py
• scripts/sigma_pipeline.sh
• scripts/sysmon_config_2025.xml

Open the folder on GitHubat commit a506ad3