Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Systematically hunt for adversary persistence mechanisms across Windows endpoints including registry, services, startup folders, and WMI subscriptions.
.claude/skills/hunting-for-persistence-mechanisms-in-windows/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | — | — |
| case-04 | ✗→✓ | ▲ Improved | — | — |
| case-01 | ✗→✓ | ▲ Improved | — | — |
| case-03 | ✗→✓ | ▲ Improved | — | — |
| case-10 | ✗→✗ | = Same ✗ | — | — |
| Concept | Description | |---------|-------------| | T1547.001 | Registry Run Keys / Startup Folder | | T1543.003 | Windows Service (Create or Modify) | | T1053.005 | Scheduled Task | | T1546.003 | WMI Event Subscription | | T1546.015 | Component Object Model (COM) Hijacking | | T1546.012 | Image File Execution Options Injection | | T1546.010 | AppInit DLLs | | T1547.004 | Winlogon Helper DLL | | T1547.005 | Security Support Provider | | T1574.001 | DLL Search Order Hijacking | | TA0003 | Persistence Tactic | | Autoruns | Sysinternals tool showing persistent entries |
| Tool | Purpose | |------|---------| | Sysinternals Autoruns | Comprehensive persistence enumeration | | Velociraptor | Endpoint-wide persistence artifact collection | | CrowdStrike Falcon | Real-time persistence monitoring | | Sysmon | Registry and WMI event monitoring | | OSQuery | SQL-based persistence queries | | RECmd | Registry Explorer for forensic analysis | | Splunk | SIEM correlation of persistence events |
HKCU\Software\Microsoft\Windows\CurrentVersion\Run entry pointing to payload in %APPDATA%.sc create pointing to a backdoor binary.Hunt ID: TH-PERSIST-[DATE]-[SEQ]
Persistence Type: [Registry/Service/Task/WMI/COM/Other]
MITRE Technique: T1547.xxx / T1543.xxx / T1053.xxx
Location: [Full registry key / service name / task path]
Value: [Binary path / command line]
Host(s): [Affected endpoints]
Signed: [Yes/No]
Hash: [SHA256]
Creation Time: [Timestamp]
Risk Level: [Critical/High/Medium/Low]
Verdict: [Malicious/Suspicious/Benign]| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +18 percentage points is the difference between those two pass rates over the 22 comparable cases.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.