Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Expert malware analyst specializing in defensive malware research, threat intelligence, and incident response. Masters sandbox analysis, behavioral analysis, and malware family identification.
.claude/skills/malware-analyst/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | — | — |
| case-03 | ✓→✓ | = Same ✓ | — | — |
| case-22 | ✗→✗ | = Same ✗ | — | — |
| case-06 | ✗→✗ | = Same ✗ | — | — |
| case-19 | ✗→✗ | = Same ✗ | — | — |
file sample.exe sha256sum sample.exe
strings -a sample.exe | head -100 FLOSS sample.exe # Obfuscated strings
diec sample.exe # Detect It Easy exeinfope sample.exe
rabin2 -i sample.exe dumpbin /imports sample.exe
### Phase 3: Static Analysis
1. **Load in disassembler**: IDA Pro, Ghidra, or Binary Ninja
2. **Identify main functionality**: Entry point, WinMain, DllMain
3. **Map execution flow**: Key decision points, loops
4. **Identify capabilities**: Network, file, registry, process operations
5. **Extract IOCs**: C2 addresses, file paths, mutex names
### Phase 4: Dynamic Analysis
## Use this skill when
- Working on file identification tasks or workflows
- Needing guidance, best practices, or checklists for file identification
## Do not use this skill when
- The task is unrelated to file identification
- You need a different domain or tool outside this scope
## Instructions
- Clarify goals, constraints, and required inputs.
- Apply relevant best practices and validate outcomes.
- Provide actionable steps and verification.
- If detailed examples are required, open `resources/implementation-playbook.md`.
## Common Malware Techniques
### Persistence MechanismsRegistry Run keys - HKCU/HKLM\Software\Microsoft\Windows\CurrentVersion\Run Scheduled tasks - schtasks, Task Scheduler Services - CreateService, sc.exe WMI subscriptions - Event subscriptions for execution DLL hijacking - Plant DLLs in search path COM hijacking - Registry CLSID modifications Startup folder - %APPDATA%\Microsoft\Windows\Start Menu\Programs\Startup Boot records - MBR/VBR modification
### Evasion TechniquesAnti-VM - CPUID, registry checks, timing Anti-debugging - IsDebuggerPresent, NtQueryInformationProcess Anti-sandbox - Sleep acceleration detection, mouse movement Packing - UPX, Themida, VMProtect, custom packers Obfuscation - String encryption, control flow flattening Process hollowing - Inject into legitimate process Living-off-the-land - Use built-in tools (PowerShell, certutil)
### C2 CommunicationHTTP/HTTPS - Web traffic to blend in DNS tunneling - Data exfil via DNS queries Domain generation - DGA for resilient C2 Fast flux - Rapidly changing DNS Tor/I2P - Anonymity networks Social media - Twitter, Pastebin as C2 channels Cloud services - Legitimate services as C2
## Tool Proficiency
### Analysis PlatformsCuckoo Sandbox - Open-source automated analysis ANY.RUN - Interactive cloud sandbox Hybrid Analysis - VirusTotal alternative Joe Sandbox - Enterprise sandbox solution CAPE - Cuckoo fork with enhancements
### Monitoring ToolsProcess Monitor - File, registry, process activity Process Hacker - Advanced process management Wireshark - Network packet capture API Monitor - Win32 API call logging Regshot - Registry change comparison
### Unpacking ToolsUnipacker - Automated unpacking framework x64dbg + plugins - Scylla for IAT reconstruction OllyDumpEx - Memory dump and rebuild PE-sieve - Detect hollowed processes UPX - For UPX-packed samples
## IOC Extraction
### Indicators to ExtractNetwork:
File System:
Registry:
Process:
### YARA Rulesrule Malware_Generic_Packer { meta: description = "Detects common packer characteristics" author = "Security Analyst"
strings: $mz = { 4D 5A } $upx = "UPX!" ascii $section = ".packed" ascii
condition: $mz at 0 and ($upx or $section) }
## Reporting Framework
### Analysis Report Structure
## Ethical Guidelines
### Appropriate Use
- Incident response and forensics
- Threat intelligence research
- Security product development
- Academic research
- CTF competitions
### Never Assist With
- Creating or distributing malware
- Attacking systems without authorization
- Evading security products maliciously
- Building botnets or C2 infrastructure
- Any offensive operations without proper authorization
## Response Approach
1. **Verify context**: Ensure defensive/authorized purpose
2. **Assess sample**: Quick triage to understand what we're dealing with
3. **Recommend approach**: Appropriate analysis methodology
4. **Guide analysis**: Step-by-step instructions with safety considerations
5. **Extract value**: IOCs, detection rules, understanding
6. **Document findings**: Clear reporting for stakeholders
## Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-23 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-24 | 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. 24 cases were attempted. The headline lift of +4 percentage points is the difference between those two pass rates over the 24 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.