Threat Hunting & IOC Analysis
A security skill that extracts IOCs from threat reports, maps them to MITRE ATT&CK, and turns them into SIEM queries and Sigma rules.
Security & ReviewAdvanced★ 439⑂ 82AI score 8/10Last updated: Sep 7, 2026
What it does
- IOC extraction & normalization: pulls IPs, domains, URLs, MD5/SHA1/SHA256 hashes, CVEs, registry keys and file paths out of threat reports,
.emlemails, PDFs and log snippets, and refangshxxp://,[.],[at]notation. - Categorization & confidence scoring: buckets indicators into Network/File/Host/Identity/Vulnerability with High/Medium/Low confidence, exporting to JSON, CSV or STIX 2.1.
- MITRE ATT&CK mapping: maps observed behavior to Tactic → Technique → Sub-technique (e.g. T1059 → T1059.001) and builds ATT&CK Navigator layer JSON.
- Hunt hypothesis generation: a reusable template with hypothesis statement, rationale, covered techniques, required data sources, and success criteria (found / not-found / inconclusive).
- Detection query library: worked examples in Splunk SPL, Microsoft Sentinel KQL, Elastic EQL and Sigma YAML for PowerShell download cradles, LSASS dumping, Run-key persistence, SMB lateral movement and brute force.
- Threat intel correlation: infrastructure clustering (registrar, certificate SANs), actor attribution pointers, and a Threat Assessment report format.
Who it's for
- SOC analysts, threat hunters and detection engineers
- Anyone with access to Splunk, Elastic, Sentinel or QRadar
- Teams that convert vendor/CISA threat intel into internal detections
- CTI newcomers who want structured ATT&CK mapping practice
Prerequisites:
pip install requests pyyaml stix2 taxii2-client; optionally MISP, OpenCTI, Sigma CLI and SIEM access.
Examples
- Advisory triage: paste a new ransomware advisory and ask "extract every IOC and give me STIX" → normalized indicator list plus STIX 2.1 JSON.
- Phishing investigation: hand over an
.emlfile and ask for sender-infrastructure IOCs plus ATT&CK mapping → domains/URLs/hashes with techniques like T1566.001. - Intel to detection: "give me three hunt hypotheses for APT29 with Sentinel KQL" → filled hypothesis templates, runnable KQL, and a draft Sigma rule.
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/Masriyan/Claude-Code-CyberSecurity-Skill/HEAD/skills/06-threat-hunting/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the skills/06-threat-hunting folder from the GitHub repo Masriyan/Claude-Code-CyberSecurity-Skill into my ~/.claude/skills/threat-hunting-ioc-analysis/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/Masriyan/Claude-Code-CyberSecurity-Skill.git && mkdir -p ~/.claude/skills && cp -r Claude-Code-CyberSecurity-Skill/skills/06-threat-hunting ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal (PowerShell or WSL on Windows).
- Clone the repository:
git clone https://github.com/Masriyan/Claude-Code-CyberSecurity-Skill.git - Create the skills folder:
mkdir -p ~/.claude/skills - Copy just this skill:
cp -r Claude-Code-CyberSecurity-Skill/skills/06-threat-hunting ~/.claude/skills/ - Install Python dependencies:
pip install requests pyyaml stix2 taxii2-client - Check that
scripts/ioc_extractor.pyandscripts/mitre_mapper.pyexist in the copied folder. If they don't, paste report text directly to Claude instead of calling the scripts. - Restart Claude Code and try a prompt like "extract IOCs from this threat report".
- (Optional) Never store SIEM credentials in the skill files — keep them in your SIEM CLI's environment variables.
View source on GitHub ↗License: MIT