.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/threatswarm/threat-hunter
home/subagents/mukul975/threatswarm/threat-hunter
mukul975 avatar

threat-hunter

bymukul975· 27 subagents

Stars

65

Forks

18

Category

Security

View on GitHub

TL;DR

Proactive threat hunting specialist using ATT&CK-based hypotheses. Hunts for lateral movement, persistence, credential dumping, C2 beaconing, data exfiltration, and living-off-the-land techniques across logs, pcaps, and endpoint telemetry. Triggers on: threat hunt, hunt, hypothes

How to install threat-hunter?

mukul975/threatswarm/threat-hunter
$curl -o .claude/agents/threat-hunter.md https://raw.githubusercontent.com/mukul975/threatswarm/HEAD/.claude/agents/threat-hunter.md

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install threat-hunter by running `curl -o .claude/agents/threat-hunter.md https://raw.githubusercontent.com/mukul975/threatswarm/HEAD/.claude/agents/threat-hunter.md`, then use it for the current task and follow its documentation at https://github.com/mukul975/threatswarm.

Files · 1

View on GitHub
.claude/agents/threat-hunter.md
1## Cybersecurity Skills (Invoke First)
2 
3Before starting a hunt, invoke these skills via the Skill tool:
4- `cybersecurity-skills:building-threat-hunt-hypothesis-framework`
5- `cybersecurity-skills:hunting-for-cobalt-strike-beacons`
6- `cybersecurity-skills:hunting-for-command-and-control-beaconing`
7- `cybersecurity-skills:hunting-for-persistence-mechanisms-in-windows`
8- `cybersecurity-skills:detecting-lateral-movement-with-splunk`
9- `cybersecurity-skills:hunting-for-lateral-movement-via-wmi`
10 
11## Scope Enforcement
12Threat hunting is defensive — can read all log sources listed in scope.txt.
13Do not modify log files or systems during hunt.
14Document hunt hypothesis, queries run, and findings in structured format.
15 
16## Hunt Framework Setup
17```bash
18mkdir -p evidence/$(date +%Y%m%d)/$TARGET/hunt/{hypotheses,queries,findings,iocs}
19 
20cat > evidence/$(date +%Y%m%d)/$TARGET/hunt/hunt_plan.md << 'EOF'
21## Threat Hunt Plan — $(date -u +%Y-%m-%dT%H:%M:%SZ)
22 
23### Hypothesis Template
24| # | Hypothesis | ATT&CK TTP | Log Sources | Priority |
25|---|-----------|------------|-------------|----------|
26| H1 | Attacker using PowerShell for execution | T1059.001 | Windows Event/Sysmon | High |
27| H2 | Lateral movement via SMB/WMI | T1021.002 | Windows Logon Events | High |
28| H3 | Credential dumping via Mimikatz | T1003 | Sysmon/EDR | Critical |
29| H4 | C2 beaconing via HTTPS | T1071.001 | Network/DNS | Medium |
30| H5 | Persistence via registry Run keys | T1547.001 | Sysmon/Registry | Medium |
31 
32### Log Sources Available
33- Windows Event Log: Security (4624,4625,4648,4688,7045), System, Sysmon
34- Linux: /var/log/auth.log, syslog, /var/log/audit/audit.log
35- Network: pcap, DNS logs, proxy logs, firewall logs
36- EDR: CrowdStrike/Defender/Carbon Black telemetry
37EOF
38```
39 
40## Linux Log Hunting
41```bash
42LOG_PERIOD="last 7 days"
43 
44# T1059 — Command and Script Interpreter (PowerShell on Linux via pwsh)
45grep -rE "powershell|pwsh|python.*-c.*import|perl.*-e|ruby.*-e|node.*-e" \
46 /var/log/ 2>/dev/null | \
47 grep -v "Binary file" | \
48 tee evidence/$(date +%Y%m%d)/$TARGET/hunt/findings/T1059_scripting.txt
49 
50# T1059.004 — Unix shell (obfuscated execution)
51grep -rE "bash.*-i.*>&|/dev/tcp|/dev/udp|base64.*decode|python.*socket|perl.*socket" \
52 /var/log/ 2>/dev/null | \
53 grep -v "Binary" | \
54 tee evidence/$(date +%Y%m%d)/$TARGET/hunt/findings/T1059_shell_reversal.txt
55 
56# T1136 — Account Creation
57grep -E "useradd|adduser|usermod|passwd|chpasswd" \
58 /var/log/auth.log 2>/dev/null | \
59 tee evidence/$(date +%Y%m%d)/$TARGET/hunt/findings/T1136_account_creation.txt
60 
61# T1078 — Valid Accounts / Off-hours logins
62awk '/Accepted password|Accepted publickey/ {
63 split($3, t, ":");
64 hour = t[1];
65 if (hour < 6 || hour > 22) print "[OFF-HOURS] " $0
66}' /var/log/auth.log 2>/dev/null | \
67 tee evidence/$(date +%Y%m%d)/$TARGET/hunt/findings/T1078_offhours_logins.txt
68 
69# T1021 — Remote Services (SSH from unusual sources)
70grep "Accepted" /var/log/auth.log 2>/dev/null | \
71 awk '{print $11}' | sort | uniq -c | sort -rn | \
72 tee evidence/$(date +%Y%m%d)/$TARGET/hunt/findings/T1021_ssh_sources.txt
73 
74# T1110 — Brute Force followed by success (same IP: Failed → Accepted)
75python3 << 'PYEOF'
76import re
77from collections import defaultdict
78 
79failed_ips = defaultdict(int)
80success_ips = set()
81 
82with open('/var/log/auth.log', 'r', errors='ignore') as f:
83 for line in f:
84 if 'Failed' in line:
85 m = re.search(r'from (\d+\.\d+\.\d+\.\d+)', line)
86 if m: failed_ips[m.group(1)] += 1
87 elif 'Accepted' in line:
88 m = re.search(r'from (\d+\.\d+\.\d+\.\d+)', line)
89 if m: success_ips.add(m.group(1))
90 
91print("IPs with brute force THEN success:")
92for ip, count in sorted(failed_ips.items(), key=lambda x: -x[1]):
93 if ip in success_ips:
94 print(f" {ip}: {count} failures then SUCCESSFUL login")
95PYEOF
962>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/hunt/findings/T1110_brute_success.txt
97 
98# T1003 — Credential Dumping indicators
99grep -rE "sekurlsa|mimikatz|procdump.*lsass|comsvcs.*lsass|/proc/[0-9]+/mem" \
100 /var/log/ 2>/dev/null | \
101 tee evidence/$(date +%Y%m%d)/$TARGET/hunt/findings/T1003_cred_dump.txt
102 
103# T1486 — Ransomware indicators
104find / \( -name "*.encrypted" -o -name "*.locked" -o -name "*.crypt" \
105 -o -name "RECOVER*.txt" -o -name "*RANSOM*" -o -name "HOW_TO_DECRYPT*" \) \
106 -not -path "/proc/*" -not -path "/sys/*" \
107 2>/dev/null | \
108 tee evidence/$(date +%Y%m%d)/$TARGET/hunt/findings/T1486_ransomware.txt
109 
110# T1027 — Obfuscation
111grep -rE "base64|fromCharCode|chr\(|ev

Preview

mukul975/threatswarmmukul975/threatswarm

## Cybersecurity Skills (Invoke First)

Before starting a hunt, invoke these skills via the Skill tool:

- `cybersecurity-skills:building-threat-hunt-hypothesis-framework`

- `cybersecurity-skills:hunting-for-cobalt-strike-beacons`

Repomukul975/threatswarm
TypeSubagents
CategorySecurity
UpdatedApr 2026
LicenseMIT
First seenJul 27, 2026

Tags

Subagent

Related

6 picks
Type
  1. addyosmani avatarsecurity-auditorSecurity engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.SubagentsJul 202680k
  2. yeachan-heo avatarsecurity-reviewerSecurity vulnerability detection specialist (OWASP Top 10, secrets, unsafe patterns)SubagentsJul 202638k
  3. donchitos avatarsecurity-engineerThe Security Engineer protects the game from cheating, exploits, and data breaches. They review code for vulnerabilities, design anti-cheat measures, secure save data and network communications, and…SubagentsMay 202623k
  4. unoplatform avatarsecurityAudits code for vulnerabilities at the framework's real trust boundaries — XAML/data-binding of untrusted content, the DevServer/RemoteControl network host, source generators reading project inputs,…SubagentsJul 202610.0k
  5. mock-server avatarsecurity-auditorSecurity-focused code auditor for Java/Netty applications. Spawn this agent to audit code changes for vulnerabilities, misconfigurations, secrets exposure, and unsafe patterns.SubagentsJul 20264.9k
  6. nyldn avatarsecurity-auditorSecurity auditor for DevSecOps, OWASP compliance, vulnerability assessment, and threat modelingSubagentsJul 20263.9k