performing-automated-malware-analysis-with-cape
Allows your agent to perform automated malware analysis in a secure sandbox environment.
What it does
This tool automatically analyzes suspicious files in a safe environment (sandbox). It observes what the file does, captures information about it, and extracts important data like configurations from known malicious programs.
When to use it
- ✓When you encounter a file that seems like a virus or malicious program.
- ✓When investigating a security incident to understand how a malicious program behaves.
- ✓To test the security of your systems in an automated way.
Example of what to ask your AI
“Analyze this suspicious file and tell me what it does.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
You send a file to the tool, which runs it in an isolated virtual computer. The tool then records all actions, network traffic, and files created by the suspicious program.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill performing-automated-malware-analysis-with-capeOr download just the file:
curl -L https://raw.githubusercontent.com/mukul975/Anthropic-Cybersecurity-Skills/main/skills/performing-automated-malware-analysis-with-cape/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
Performing Automated Malware Analysis with CAPE
Overview
CAPE (Config And Payload Extraction) is an open-source malware sandbox derived from Cuckoo that automates behavioral analysis, payload dumping, and configuration extraction. CAPEv2 features API hooking for behavioral instrumentation, captures files created/modified/deleted during execution, records network traffic in PCAP format, and includes 70+ custom configuration extractors (cape-parsers) for families like Emotet, TrickBot, Cobalt Strike, AsyncRAT, and Rhadamanthys. The signature system includes 1000+ behavioral signatures detecting evasion techniques, persistence, credential theft, and ransomware behavior. CAPE's debugger enables dynamic anti-evasion bypasses combining debugger actions within YARA signatures. Recommended deployment: Ubuntu LTS host with Windows 10 21H2 guest VM.
When to Use
- When conducting security assessments that involve performing automated malware analysis with cape
- When following incident response procedures for related security events
- When performing scheduled security testing or auditing activities
- When validating security controls through hands-on testing
Prerequisites
- Ubuntu 22.04 LTS server (8+ CPU cores, 32GB+ RAM, 500GB+ SSD)
- KVM/QEMU virtualization support
- Windows 10 21H2 guest image
- Python 3.9+ with CAPEv2 dependencies
- Network configuration for isolated analysis network
Workflow
Step 1: Submit and Analyze Samples via API
#!/usr/bin/env python3
"""CAPE sandbox API client for automated malware submission and analysis."""
import requests
import json
import time
import sys
from pathlib import Path
class CAPEClient:
def __init__(self, base_url="http://localhost:8000", api_token=None):
self.base_url = base_url.rstrip("/")
self.headers = {}
if api_token:
self.headers["Authorization"] = f"Token {api_token}"
def submit_file(self, filepath, options=None):
"""Submit a file for analysis."""
url = f"{self.base_url}/apiv2/tasks/create/file/"
files = {"file": open(filepath, "rb")}
data = options or {}
data.setdefault("timeout", 120)
data.setdefault("enforce_timeout", False)
resp = requests.post(url, files=files, data=data, headers=self.headers)
resp.raise_for_status()
result = resp.json()
task_id = result.get("data", {}).get("task_ids", [None])[0]
print(f"[+] Submitted {filepath} -> Task ID: {task_id}")
return task_id
def get_status(self, task_id):
"""Check task analysis status."""
url = f"{self.base_url}/apiv2/tasks/status/{task_id}/"
resp = requests.get(url, headers=self.headers)
return resp.json().get("data", "unknown")
def wait_for_completion(self, task_id, poll_interval=15, max_wait=600):
"""Wait for analysis to complete."""
elapsed = 0
while elapsed < max_wait:
status = self.get_status(task_id)
if status == "reported":
print(f"[+] Task {task_id} completed")
return True
time.sleep(poll_interval)
elapsed += poll_interval
print(f" Waiting... ({elapsed}s, status: {status})")
return False
def get_report(self, task_id):
"""Retrieve full analysis report."""
url = f"{self.base_url}/apiv2/tasks/get/report/{task_id}/"
resp = requests.get(url, headers=self.headers)
return resp.json()
def get_config(self, task_id):
"""Get extracted malware configuration."""
report = self.get_report(task_id)
configs = report.get("CAPE", {}).get("configs", [])
return configs
def get_dropped_files(self, task_id):
"""List files dropped during analysis."""
report = self.get_report(task_id)
return report.get("dropped", [])
def get_network_iocs(self, task_id):
"""Extract network IOCs from analysis."""
report = self.get_report(task_id)
network = report.get("network", {})
iocs = {
"dns": [d.get("request") for d in network.get("dns", [])],
"http": [h.get("uri") for h in network.get("http", [])],
"tcp": [f"{h.get('dst')}:{h.get('dport')}"
for h in network.get("tcp", [])],
}
return iocs
def analyze_sample(self, filepath):
"""Full automated analysis pipeline."""
…
FAQ
What is a 'sandbox'?
It's a safe and isolated environment, like a sandbox, where a program can be run without affecting your real computer.
What are 'behavioral signatures'?
These are patterns of behavior that the tool looks for to identify specific types of malicious programs.
What are 'IOCs'?
IOCs (Indicators of Compromise) are clues that help identify malicious activity, such as website addresses or IPs the program tried to contact.
Details
Original description by the author
Deploy and operate the CAPEv2 malware sandbox (a Cuckoo derivative) to run samples in a monitored Windows guest VM, capturing behavioral signatures, dropped files, PCAP network traffic, and family-specific configuration extraction (e.g. Emotet, TrickBot, Cobalt Strike) via cape-parsers. Use when a suspicious file or payload needs automated dynamic analysis, anti-evasion debugger tricks, or config/
Popularity
- GitHub stars
- 35k
- Ranking position
- #6026
- License
- Apache-2.0
- Updated
- 8/31/2026
Comments
- …
More skills from this repository
abusing-dpapi-for-credential-access
Gives your AI agent ready-made instructions for a specific task, so it does it better and faster.
mukul975/Anthropic-Cybersecurity-Skills
abusing-shadow-credentials-for-privesc
Teaches your AI agent to write clear, well-structured text.
mukul975/Anthropic-Cybersecurity-Skills
achieving-cmmc-level-2-compliance
Helps your agent prepare an environment for CMMC Level 2 compliance. It implements security requirements and manages necessary documentation.
mukul975/Anthropic-Cybersecurity-Skills
acquiring-disk-image-with-dd-and-dcfldd
Helps your agent create exact copies of hard drives. This is useful for ensuring no information is lost or altered during investigations.
mukul975/Anthropic-Cybersecurity-Skills
Similar skills
dashboard-builder
Helps your agent create useful monitoring dashboards. It turns data into charts that answer important system questions.
affaan-m/ECC
dev-team
Simulates a collaborative development team where different roles respond to a problem together. It's useful for getting multiple perspectives without manually switching agents.
affaan-m/ECC
ecc-council
Has your agent convene a four-voice council for difficult decisions. It's useful when there are multiple good options and debate is needed before choosing.
affaan-m/ECC