Add Community Skill
samugit83/redamon
Adding a Community Agent Skill: a Markdown attack-workflow file that users import from the catalog, which then competes in the Intent Router and is injected into the agent's system prompt.
Agent skill
Analyzes malware C2 communication over HTTP, HTTPS, DNS, and custom protocols to reverse-engineer beacon patterns, command structures, data encoding, and infrastructure (primary servers, fallback…
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill analyzing-command-and-control-communication -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills analyzing-command-and-control-communication --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/analyzing-command-and-control-communication .claude/skills/analyzing-command-and-control-communication && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "analyzing-command-and-control-communication" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/analyzing-command-and-control-communication into .claude/skills/analyzing-command-and-control-communication/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "analyzing-command-and-control-communication", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/analyzing-command-and-control-communicationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill analyzing-command-and-control-communication -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills analyzing-command-and-control-communication --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/analyzing-command-and-control-communication .agents/skills/analyzing-command-and-control-communication && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "analyzing-command-and-control-communication" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/analyzing-command-and-control-communication into .agents/skills/analyzing-command-and-control-communication/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "analyzing-command-and-control-communication", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill analyzing-command-and-control-communication -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills analyzing-command-and-control-communication --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/analyzing-command-and-control-communication .cursor/skills/analyzing-command-and-control-communication && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "analyzing-command-and-control-communication" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/analyzing-command-and-control-communication into .cursor/skills/analyzing-command-and-control-communication/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "analyzing-command-and-control-communication", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git --path skills/analyzing-command-and-control-communication--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill analyzing-command-and-control-communication -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills analyzing-command-and-control-communication --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/analyzing-command-and-control-communication .gemini/skills/analyzing-command-and-control-communication && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "analyzing-command-and-control-communication" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/analyzing-command-and-control-communication into .gemini/skills/analyzing-command-and-control-communication/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "analyzing-command-and-control-communication", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills analyzing-command-and-control-communicationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill analyzing-command-and-control-communication -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/analyzing-command-and-control-communication .github/skills/analyzing-command-and-control-communication && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "analyzing-command-and-control-communication" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/analyzing-command-and-control-communication into .github/skills/analyzing-command-and-control-communication/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "analyzing-command-and-control-communication", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill analyzing-command-and-control-communication -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills analyzing-command-and-control-communication --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/analyzing-command-and-control-communication .opencode/skills/analyzing-command-and-control-communication && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "analyzing-command-and-control-communication" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/analyzing-command-and-control-communication into .opencode/skills/analyzing-command-and-control-communication/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "analyzing-command-and-control-communication", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
analyzing-command-and-control-communicationAnalyzes malware C2 communication over HTTP, HTTPS, DNS, and custom protocols to reverse-engineer beacon patterns, command structures, data encoding, and infrastructure (primary servers, fallback…
Analyzing Command And Control Communication is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Analyzes malware C2 communication over HTTP, HTTPS, DNS, and custom protocols to reverse-engineer beacon patterns, command structures, data encoding, and infrastructure (primary servers, fallback domains, dead drops). Use after reverse engineering reveals network traffic needing protocol analysis or when building detection signatures for a framework like Cobalt Strike, Metasploit, or Sliver.
Its SKILL.md is about 3.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `references/api-reference.md` and `scripts/agent.py`).
It sits in Security, covering Red teaming and adversary simulation, Reverse engineering and malware and Penetration testing. It works with Metasploit. The repository describes itself as: 817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io…. The licence is Apache-2.0.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 54a7988. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
api.shodan.iovirustotal.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
VT_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Analyzing Command And Control Communication loads about 3.6k tokens when it runs, and up to ~4.3k if it reads all its reference files. Until then it costs about 110 tokens; SKILL.md has 619 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from mukul975/Anthropic-Cybersecurity-Skills at commit 54a7988, republished under its Apache-2.0 licence (© mukul975). 619 words, ~3,591 tokens.
.claude/skills/analyzing-command-and-control-communication/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.Do not use for general network anomaly detection; this is specifically for understanding known or suspected C2 protocols from malware analysis.
scapy, dpkt, and requests for protocol analysis and replayDetermine the protocol and transport used for C2 communication:
C2 Communication Channels:
━━━━━━━━━━━━━━━━━━━━━━━━━
HTTP/HTTPS: Most common; uses standard web traffic to blend in
Indicators: Regular POST/GET requests, specific URI patterns, custom headers
DNS: Tunneling data through DNS queries and responses
Indicators: High-volume TXT queries, long subdomain names, high entropy
Custom TCP/UDP: Proprietary binary protocol on non-standard port
Indicators: Non-HTTP traffic on high ports, unknown protocol
ICMP: Data encoded in ICMP echo/reply payloads
Indicators: ICMP packets with large or non-standard payloads
WebSocket: Persistent bidirectional connection for real-time C2
Indicators: WebSocket upgrade followed by binary frames
Cloud Services: Using legitimate APIs (Telegram, Discord, Slack, GitHub)
Indicators: API calls to cloud services from unexpected processes
Email: SMTP/IMAP for C2 commands and data exfiltration
Indicators: Automated email operations from non-email processesCharacterize the periodic communication pattern:
from scapy.all import rdpcap, IP, TCP
from collections import defaultdict
import statistics
import json
packets = rdpcap("c2_traffic.pcap")
# Group TCP SYN packets by destination
connections = defaultdict(list)
for pkt in packets:
if IP in pkt and TCP in pkt and (pkt[TCP].flags & 0x02):
key = f"{pkt[IP].dst}:{pkt[TCP].dport}"
connections[key].append(float(pkt.time))
# Analyze each destination for beaconing
for dst, times in sorted(connections.items()):
if len(times) < 3:
continue
intervals = [times[i+1] - times[i] for i in range(len(times)-1)]
avg_interval = statistics.mean(intervals)
stdev = statistics.stdev(intervals) if len(intervals) > 1 else 0
jitter_pct = (stdev / avg_interval * 100) if avg_interval > 0 else 0
duration = times[-1] - times[0]
beacon_data = {
"destination": dst,
"connections": len(times),
"duration_seconds": round(duration, 1),
"avg_interval_seconds": round(avg_interval, 1),
"stdev_seconds": round(stdev, 1),
"jitter_percent": round(jitter_pct, 1),
"is_beacon": 5 < avg_interval < 7200 and jitter_pct < 25,
}
if beacon_data["is_beacon"]:
print(f"[!] BEACON DETECTED: {dst}")
print(f" Interval: {avg_interval:.0f}s +/- {stdev:.0f}s ({jitter_pct:.0f}% jitter)")
print(f" Sessions: {len(times)} over {duration:.0f}s")Reverse engineer the message format from captured traffic:
# HTTP-based C2 protocol analysis
import dpkt
import base64
with open("c2_traffic.pcap", "rb") as f:
pcap = dpkt.pcap.Reader(f)
for ts, buf in pcap:
eth = dpkt.ethernet.Ethernet(buf)
if not isinstance(eth.data, dpkt.ip.IP):
continue
ip = eth.data
if not isinstance(ip.data, dpkt.tcp.TCP):
continue
tcp = ip.data
if tcp.dport == 80 or tcp.dport == 443:
if len(tcp.data) > 0:
try:
http = dpkt.http.Request(tcp.data)
print(f"\n--- C2 REQUEST ---")
print(f"Method: {http.method}")
print(f"URI: {http.uri}")
print(f"Headers: {dict(http.headers)}")
if http.body:
print(f"Body ({len(http.body)} bytes):")
# Try Base64 decode
try:
decoded = base64.b64decode(http.body)
print(f" Decoded: {decoded[:200]}")
except:
print(f" Raw: {http.body[:200]}")
except:
passMatch observed patterns to known C2 frameworks:
Known C2 Framework Signatures:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Cobalt Strike:
- Default URIs: /pixel, /submit.php, /___utm.gif, /ca, /dpixel
- Malleable C2 profiles customize all traffic characteristics
- JA3: varies by profile, catalog at ja3er.com
- Watermark in beacon config (unique per license)
- Config extraction: use CobaltStrikeParser or 1768.py
Metasploit/Meterpreter:
- Default staging URI patterns: random 4-char checksum
- Reverse HTTP(S) handler patterns
- Meterpreter TLV (Type-Length-Value) protocol structure
Sliver:
- mTLS, HTTP, DNS, WireGuard transport options
- Protobuf-encoded messages
- Unique implant ID in communication
Covenant:
- .NET-based C2 framework
- HTTP with customizable profiles
- Task-based command execution
PoshC2:
- PowerShell/C# based
- HTTP with encrypted payloads
- Cookie-based session management# Extract Cobalt Strike beacon configuration from PCAP or sample
python3 << 'PYEOF'
# Using CobaltStrikeParser (pip install cobalt-strike-parser)
from cobalt_strike_parser import BeaconConfig
try:
config = BeaconConfig.from_file("suspect.exe")
print("Cobalt Strike Beacon Configuration:")
for key, value in config.items():
print(f" {key}: {value}")
except Exception as e:
print(f"Not a Cobalt Strike beacon or parse error: {e}")
PYEOFDocument the full C2 infrastructure and failover mechanisms:
# Infrastructure mapping
import requests
import json
c2_indicators = {
"primary_c2": "185.220.101.42",
"domains": ["update.malicious.com", "backup.evil.net"],
"ports": [443, 8443],
"failover_dns": ["ns1.malicious-dns.com"],
}
# Enrich with Shodan
def shodan_lookup(ip, api_key):
resp = requests.get(f"https://api.shodan.io/shodan/host/{ip}?key={api_key}")
if resp.status_code == 200:
data = resp.json()
return {
"ip": ip,
"ports": data.get("ports", []),
"os": data.get("os"),
"org": data.get("org"),
"asn": data.get("asn"),
"country": data.get("country_code"),
"hostnames": data.get("hostnames", []),
"last_update": data.get("last_update"),
}
return None
# Enrich with passive DNS
def pdns_lookup(domain):
# Using VirusTotal passive DNS
resp = requests.get(
f"https://www.virustotal.com/api/v3/domains/{domain}/resolutions",
headers={"x-apikey": VT_API_KEY}
)
if resp.status_code == 200:
data = resp.json()
resolutions = []
for r in data.get("data", []):
resolutions.append({
"ip": r["attributes"]["ip_address"],
"date": r["attributes"]["date"],
})
return resolutions
return []Build detection rules based on analyzed C2 characteristics:
# Suricata rules for the analyzed C2
cat << 'EOF' > c2_detection.rules
# HTTP beacon pattern
alert http $HOME_NET any -> $EXTERNAL_NET any (
msg:"MALWARE MalwareX C2 HTTP Beacon";
flow:established,to_server;
http.method; content:"POST";
http.uri; content:"/gate.php"; startswith;
http.header; content:"User-Agent: Mozilla/5.0 (compatible; MSIE 10.0)";
threshold:type threshold, track by_src, count 5, seconds 600;
sid:9000010; rev:1;
)
# JA3 fingerprint match
alert tls $HOME_NET any -> $EXTERNAL_NET any (
msg:"MALWARE MalwareX TLS JA3 Fingerprint";
ja3.hash; content:"a0e9f5d64349fb13191bc781f81f42e1";
sid:9000011; rev:1;
)
# DNS beacon detection (high-entropy subdomain)
alert dns $HOME_NET any -> any any (
msg:"MALWARE Suspected DNS C2 Tunneling";
dns.query; pcre:"/^[a-z0-9]{20,}\./";
threshold:type threshold, track by_src, count 10, seconds 60;
sid:9000012; rev:1;
)
# Certificate-based detection
alert tls $HOME_NET any -> $EXTERNAL_NET any (
msg:"MALWARE MalwareX Self-Signed C2 Certificate";
tls.cert_subject; content:"CN=update.malicious.com";
sid:9000013; rev:1;
)
EOF| Term | Definition |
|---|---|
| Beaconing | Periodic check-in communication from malware to C2 server at regular intervals, often with jitter to avoid pattern detection |
| Jitter | Randomization applied to beacon interval (e.g., 60s +/- 15%) to make the timing pattern less predictable and harder to detect |
| Malleable C2 | Cobalt Strike feature allowing operators to customize all aspects of C2 traffic (URIs, headers, encoding) to mimic legitimate services |
| Dead Drop | Intermediate location (paste site, cloud storage, social media) where C2 commands are posted for the malware to retrieve |
| Domain Fronting | Using a trusted CDN domain in the TLS SNI while routing to a different backend, making C2 traffic appear to go to a legitimate service |
| Fast Flux | Rapidly changing DNS records for C2 domains to distribute across many IPs and resist takedown efforts |
| C2 Framework | Software toolkit providing C2 server, implant generator, and operator interface (Cobalt Strike, Metasploit, Sliver, Covenant) |
Context: A malware sample communicates with its C2 server using an unknown binary protocol over TCP port 8443. The protocol needs to be decoded to understand the command set and build detection signatures.
Approach:
Pitfalls:
C2 COMMUNICATION ANALYSIS REPORT
===================================
Sample: malware.exe (SHA-256: e3b0c44...)
C2 Framework: Cobalt Strike 4.9
BEACON CONFIGURATION
C2 Server: hxxps://185.220.101[.]42/updates
Beacon Type: HTTPS (reverse)
Sleep: 60 seconds
Jitter: 15%
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64)
URI (GET): /dpixel
URI (POST): /submit.php
Watermark: 1234567890
PROTOCOL ANALYSIS
Transport: HTTPS (TLS 1.2)
JA3 Hash: a0e9f5d64349fb13191bc781f81f42e1
Certificate: CN=Microsoft Update (self-signed)
Encoding: Base64 with XOR key 0x69
Command Format: [4B length][4B command_id][payload]
COMMAND SET
0x01 - Sleep Change beacon interval
0x02 - Shell Execute cmd.exe command
0x03 - Download Transfer file from C2
0x04 - Upload Exfiltrate file to C2
0x05 - Inject Process injection
0x06 - Keylog Start keylogger
0x07 - Screenshot Capture screen
INFRASTRUCTURE
Primary: 185.220.101[.]42 (AS12345, Hosting Co, NL)
Failover: 91.215.85[.]17 (AS67890, VPS Provider, RU)
DNS: update.malicious[.]com -> 185.220.101[.]42
Registrar: NameCheap
Registration: 2025-09-01
DETECTION SIGNATURES
SID 9000010: HTTP beacon pattern
SID 9000011: JA3 TLS fingerprint
SID 9000013: C2 certificate match© mukul975, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files (scripts, references) in skills/analyzing-command-and-control-communication of mukul975/Anthropic-Cybersecurity-Skills.
Open the folder on GitHubat commit 54a7988
Analyzing Command And Control Communication next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Analyzing Command And Control Communication this skillmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~3.6k | Automated safety check: Pass | Apache-2.0 | |
| Add Community Skillsamugit83/redamon | 3k | — | ~775 | Automated safety check: Pass | MIT | |
| MetasploitEncod3d-Sec/TORCH | 329 | — | ~1k | Automated safety check: Pass | MIT | |
| Incident Response NetworkLeoYeAI/openclaw-master-skills | 2.2k | — | ~5k | Automated safety check: Pass | Apache-2.0 | |
| Client Request Signature Reversalawarexone/Agentic-Bug-Hunter | 5.3k | — | ~4.7k | Automated safety check: Pass | MIT | |
| Penetration Flowlingbol088-spec/ReiPenFlow | 222 | — | ~1.8k | Automated safety check: Pass | MIT |
samugit83/redamon
Adding a Community Agent Skill: a Markdown attack-workflow file that users import from the catalog, which then competes in the Intent Router and is injected into the agent's system prompt.
Encod3d-Sec/TORCH
Drive msfconsole across the workflow - DB-backed recon (dbnmap, auxiliary scanners), version-exploit search/check/run, multi/handler reverse shells (meterpreter-first, plain shellreversetcp backup…
LeoYeAI/openclaw-master-skills
Network forensics evidence collection and analysis during security incidents.
awarexone/Agentic-Bug-Hunter
Recovers a client-side request signature or anti-bot token just far enough to replay blocked requests in bug bounty testing, starting from a captured packet.
lingbol088-spec/ReiPenFlow
Guided workflow for authorized penetration testing, vulnerability validation, security reporting, CTF/local sandbox reverse engineering, and user-directed vulnerability research.
Encod3d-Sec/TORCH
Runs a capture-the-flag box from first scan to root with a driver script that tracks progress and prints the next action each turn.
mukul975/Anthropic-Cybersecurity-Skills
Weighs infrastructure, TTP, malware code and timing evidence with the Diamond Model and competing hypotheses to reach a confidence-rated attribution.
mukul975/Anthropic-Cybersecurity-Skills
Walks through reverse engineering Go-compiled malware in Ghidra: parsing buildinfo and pclntab, recovering stripped function names and extracting dependencies.
mukul975/Anthropic-Cybersecurity-Skills
Guides forensic analysis of Windows LNK shortcut files and Jump Lists with LECmd, JLECmd and manual parsing to show file access and program execution.
mukul975/Anthropic-Cybersecurity-Skills
Hunts Windows malware persistence with Sysinternals Autoruns, covering run keys, services, scheduled tasks and drivers, with baseline comparison.
mukul975/Anthropic-Cybersecurity-Skills
Guides a Windows forensic examination of the NTFS Master File Table to recover deleted-file evidence, build timelines and spot timestomping.
mukul975/Anthropic-Cybersecurity-Skills
Detects DNS tunneling, ICMP exfiltration and HTTP-based covert channels in packet captures and DNS logs when hunting for hidden command-and-control traffic.
Works with
Categories
Analyzes malware C2 communication over HTTP, HTTPS, DNS, and custom protocols to reverse-engineer beacon patterns, command structures, data encoding, and infrastructure (primary servers, fallback…. Analyzing Command And Control Communication is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Analyzes malware C2 communication over HTTP, HTTPS, DNS, and custom protocols to reverse-engineer beacon patterns, command structures, data encoding, and infrastructure (primary servers, fallback domains, dead drops).
Analyzing Command And Control Communication fits situations like: tasks that involve Red teaming and adversary simulation; tasks that involve Reverse engineering and malware; tasks that involve Penetration testing.
Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill analyzing-command-and-control-communication -a claude-code`. Or copy the skill folder (skills/analyzing-command-and-control-communication in mukul975/Anthropic-Cybersecurity-Skills) into .claude/skills/analyzing-command-and-control-communication in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill analyzing-command-and-control-communication -a codex`. Or copy the skill folder (skills/analyzing-command-and-control-communication in mukul975/Anthropic-Cybersecurity-Skills) into .agents/skills/analyzing-command-and-control-communication in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill analyzing-command-and-control-communication -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/analyzing-command-and-control-communication, .gemini/skills/analyzing-command-and-control-communication, .github/skills/analyzing-command-and-control-communication and .opencode/skills/analyzing-command-and-control-communication in your project.
Going by SKILL.md and its folder, Analyzing Command And Control Communication needs Python for the scripts in its folder, the command-line tools its instructions call (python3) and credentials named VT_API_KEY. Our summary lists: Python 3; A credential in VT_API_KEY.
SKILL.md names 2 domains. In commands or code: api.shodan.io and virustotal.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Analyzing Command And Control Communication is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.6k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 689 tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Analyzing Command And Control Communication: Add Community Skill (samugit83/redamon, 3k stars), Metasploit (Encod3d-Sec/TORCH, 329 stars), Incident Response Network (LeoYeAI/openclaw-master-skills, 2.2k stars) and Client Request Signature Reversal (awarexone/Agentic-Bug-Hunter, 5.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
mukul975 (a GitHub user) maintains it in mukul975/Anthropic-Cybersecurity-Skills, which has 33,922 GitHub stars. The repository holds 637 skills in this directory. The repository was last updated on August 31, 2026.
Source: mukul975/Anthropic-Cybersecurity-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.