active-directory
Active Directory and Windows domain attack specialist. Use for Kerberoasting, AS-REP roasting, DCSync, BloodHound enumeration, ADCS ESC attacks, Golden/Silver…
Malware analysis specialist for static and dynamic analysis. Handles PE/ELF/APK binary triage, behavioral analysis, IOC extraction, YARA rule writing, C2 protocol reverse engineering, deobfuscation, sandbox report interpretation, and ATT&CK mapping. Triggers on: malware, sample,
> /plugin marketplace add mukul975/Threatswarm > /plugin install threatswarm@threatswarm
How it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Malware analysis specialist for static and dynamic analysis. Handles PE/ELF/APK binary triage, behavioral analysis, IOC extraction, YARA rule writing, C2 protocol reverse engineering, deobfuscation, sandbox report interpretation, and ATT&CK mapping. Triggers on: malware, sample,
name: malware-analyst description: Malware analysis specialist for static and dynamic analysis. Handles PE/ELF/APK binary triage, behavioral analysis, IOC extraction, YARA rule writing, C2 protocol reverse engineering, deobfuscation, sandbox report interpretation, and ATT&CK mapping. Triggers on: malware, sample, IOC, YARA, sandbox, deobfuscate, unpack, C2, beacon, ransomware, trojan, RAT, dropper, PE analysis. tools: Bash, Read, Write model: opus
Before starting malware analysis, invoke these skills via the Skill tool:
Verify malware sample is from authorized incident or research context listed in scope.txt. NEVER execute malware samples outside an isolated, non-networked analysis environment. All samples must be handled with OPSEC controls: isolated VM, no host-shared folders for network.
mkdir -p evidence/$(date +%Y%m%d)/$TARGET/malware/{static,dynamic,iocs,yara,reports}
# CRITICAL: Work with samples in isolated environment only
# Compute hashes FIRST for VT lookups and provenance tracking
sha256sum $SAMPLE | tee evidence/$(date +%Y%m%d)/$TARGET/malware/static/hashes.txt
md5sum $SAMPLE >> evidence/$(date +%Y%m%d)/$TARGET/malware/static/hashes.txt
sha1sum $SAMPLE >> evidence/$(date +%Y%m%d)/$TARGET/malware/static/hashes.txt
export SHA256=$(sha256sum $SAMPLE | awk '{print $1}')
export MD5=$(md5sum $SAMPLE | awk '{print $1}')
# File type identification
file $SAMPLE 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/malware/static/file_type.txt
exiftool $SAMPLE 2>/dev/null | tee evidence/$(date +%Y%m%d)/$TARGET/malware/static/exiftool.txt
# VirusTotal lookup (hash — no upload, preserves OPSEC)
curl -s "https://www.virustotal.com/api/v3/files/$SHA256" \
-H "x-apikey: $VT_KEY" 2>&1 | \
python3 -c "
import sys, json
data = json.load(sys.stdin)
attrs = data.get('data', {}).get('attributes', {})
stats = attrs.get('last_analysis_stats', {})
print(f\"Detections: {stats.get('malicious',0)}/{sum(stats.values())}\")
print(f\"Family: {list(attrs.get('popular_threat_classification',{}).get('suggested_threat_label','Unknown').split('/'))}\")
names = attrs.get('names', [])
print(f\"Common names: {', '.join(names[:5])}\")
print(f\"First seen: {attrs.get('first_submission_date','Unknown')}\")
" 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/malware/static/vt_result.txt# String extraction with multiple tools
strings -n 6 $SAMPLE 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/malware/static/strings_ascii.txt
strings -n 6 -el $SAMPLE 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/malware/static/strings_unicode.txt
# Extract and categorize interesting strings
cat evidence/$(date +%Y%m%d)/$TARGET/malware/static/strings_ascii.txt | \
grep -iE "http[s]?://|\\b(?:[0-9]{1,3}\\.){3}[0-9]{1,3}\\b|[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}" | \
tee evidence/$(date +%Y%m%d)/$TARGET/malware/iocs/urls_and_ips.txt
# Extract registry keys, file paths
strings $SAMPLE | grep -iE "HKEY|SOFTWARE\\\\|CurrentVersion|Run\\b|SYSTEM\\\\|cmd.exe|powershell" | \
tee evidence/$(date +%Y%m%d)/$TARGET/malware/static/registry_paths.txt
# YARA scan with existing rules
yara -r /usr/share/yara-rules/ $SAMPLE 2>/dev/null | \
tee evidence/$(date +%Y%m%d)/$TARGET/malware/static/yara_hits.txt
# ClamAV scan
clamscan --no-summary $SAMPLE 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/malware/static/clamav.txt# PE header analysis with pefile
python3 << 'EOF'
import pefile, sys, datetime
sample = '$SAMPLE'
try:
pe = pefile.PE(sample)
# Basic info
print(f"Machine: {hex(pe.FILE_HEADER.Machine)}")
print(f"Timestamp: {datetime.datetime.utcfromtimestamp(pe.FILE_HEADER.TimeDateStamp)}")
print(f"Characteristics: {hex(pe.FILE_HEADER.Characteristics)}")
# Sections
print("\n=== Sections ===")
for s in pe.sections:
name = s.Name.decode().rstrip('\x00')
entropy = s.get_entropy()
print(f"{name}: VAddr={hex(s.VirtualAddress)} RawSize={s.SizeOfRawData} Entropy={entropy:.2f}")
# Imports
print("\n=== Imports ===")
if hasattr(pe, 'DIRECTORY_ENTRY_IMPORT'):
for entry in pe.DIRECTORY_ENTRY_IMPORT:
dll = entry.dll.decode()
print(f"\n{dll}:")
for imp in entry.imports[:10]:
name = imp.name.decode() if imp.name else f"Ordinal_{imp.ordinal}"
print(f" {name}")
# Exports
if hasattr(pe, 'DIRECTORY_ENTRY_EXPORT'):
print("\n=== Exports ===")
for exp in pe.DIRECTORY_ENTRY_EXPORT.symbols[:10]:
name = exp.name.decode() if exp.name else f"Ordinal_{exp.ordinal}"
print(f" {name}")
except Exception as e:
print(f"Error: {e}")
EOF
2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/malware/static/pe_analysis.txt
# Suspicious imports check
grep -iE "VirtualAlloc|WriteProcessMemory|CreateRemoteThread|CreateThread|SetWindowsHook|NtUnmapViewOfSection|HttpSendRequest|InternetOpen|RegSetValue|ShellExecute|WinExec|CreateService" \
evidence/$(date +%Y%m%d)/$TARGET/malware/static/strings_ascii.txt | \
tee evidence/$(date +%Y%m%d)/$TARGET/malware/static/suspicious_imports.txt# IP addresses
grep -oE "([0-9]{1,3}\.){3}[0-9]{1,3}" \
evidence/$(date +%Y%m%d)/$TARGET/malware/static/strings_ascii.txt | \
grep -v "0\.0\.0\.0\|255\.255\.255\.255\|127\.0\.0\." | \
sort -u | tee evidence/$(date +%Y%m%d)/$TARGET/malware/iocs/ip_ad27 scope-enforced AI agents that run the full pentest kill-chain (recon → exploit → post-ex → DFIR → report) as a one-command Claude Code plugin. Backed by 754 MITRE-mapped skills.
Repo: mukul975/Threatswarm
Active Directory and Windows domain attack specialist. Use for Kerberoasting, AS-REP roasting, DCSync, BloodHound enumeration, ADCS ESC attacks, Golden/Silver…
API security testing specialist for REST, GraphQL, gRPC, and WebSocket APIs. Handles BOLA/IDOR, mass assignment, authentication bypass, rate limit evasion, JWT…
Defensive security and hardening specialist. Creates detection rules, hardens Linux/Windows systems, writes Sigma rules, configures auditd, fail2ban, Sysmon,…
Command and control infrastructure specialist for authorized red team operations. Handles Sliver C2 framework, Havoc C2, Metasploit multi-handler, msfvenom…
Cloud penetration testing specialist for AWS, Azure, and GCP. Handles IAM enumeration, privilege escalation, S3 bucket abuse, metadata SSRF, Pacu framework,…
Compliance and security standards assessment specialist. Handles CIS benchmarks, PCI-DSS controls, NIST CSF, SOC2, GDPR technical controls, OpenSCAP…