performing-automated-malware-analysis-with-cape

performing-automated-malware-analysis-with-cape is a skill for Claude Code, Codex from adriannoes/awesome-agentic-ai. It costs 39 tokens per session (1,532 once invoked), scanned A, original, MIT.

A workflow for running CAPEv2, an isolated environment that executes suspicious files and records what they do. It can extract payloads and settings while capturing behavior, changed files, and network traffic.

In plain words
What is it for?
Use it to analyze suspicious programs, extract malware payloads and configurations, inspect network traffic, and support incident response.
Why use it?
It gives analysts evidence about malware behavior without relying only on static file inspection. This helps identify evasion, persistence, credential theft, and ransomware activity.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to analyze suspicious programs, extract malware payloads and configurations, inspect network traffic, and support incident response.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adriannoes/awesome-agentic-ai/performing-automated-malware-analysis-with-cape
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add adriannoes/awesome-agentic-ai --skill performing-automated-malware-analysis-with-cape
Clone the repo
git clone --depth 1 https://github.com/adriannoes/awesome-agentic-ai

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for performing-automated-malware-analysis-with-cape

README.md
[![agentmods](https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/performing-automated-malware-analysis-with-cape/github.svg)](https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/performing-automated-malware-analysis-with-cape)
Your own site
<a href="https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/performing-automated-malware-analysis-with-cape"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/performing-automated-malware-analysis-with-cape/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for performing-automated-malware-analysis-with-cape

Your own site · 80×15
<a href="https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/performing-automated-malware-analysis-with-cape"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/performing-automated-malware-analysis-with-cape.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,532 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.01532
Opus 5 $0.00019 $0.00766
Sonnet 5 $0.00008 $0.00306
Haiku 4.5 $0.00004 $0.00153

Measured 9d ago against content hash 9306134d7383, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

performing-automated-malware-analysis-with-cape scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/agent.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

resp = requests.post(url, files=files, data=data, headers=self.headers)
cursor-claude-codex/skills/anthropic-cybersecurity-skills/skills/performing-automated-malware-analysis-with-cape/SKILL.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on 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."""
        task_id = self.submit_file(filepath)
        if not task_id:
            return None

        if self.wait_for_completion(task_id):
            report = {
                "task_id": task_id,
                "config": self.get_config(task_id),
                "network_iocs": self.get_network_iocs(task_id),
                "dropped_files": len(self.get_dropped_files(task_id)),
            }
            return report
        return None


if __name__ == "__main__":
    if len(sys.argv) < 2:
        print(f"Usage: {sys.argv[0]} <malware_sample> [cape_url]")
        sys.exit(1)

    url = sys.argv[2] if len(sys.argv) > 2 else "http://localhost:8000"
    client = CAPEClient(url)
    result = client.analyze_sample(sys.argv[1])
    if result:
        print(json.dumps(result, indent=2))

Read the full file on GitHub · 181 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 181 lines · 39 tokens per session scan A 9306134d7383

Subscribe to this mod's changes

performing-automated-malware-analysis-with-cape is a skill published in the GitHub repository adriannoes/awesome-agentic-ai (57 stars, last pushed 14d ago), licensed MIT. It adds 39 tokens to every session and 1,532 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

analyzing-malware-behavior-with-cuckoo-sandbox

Executes malware samples in Cuckoo Sandbox to observe runtime behavior including process creation, file system modifications, registry changes, network communications, and API calls. Generates comprehensive behavioral reports for malware classification and IOC extraction. Activates for requests involving dynamic…

marysatasselshaped667/skills-collection-1 · 78 tokens

analyzing-malware-sandbox-evasion-techniques

Detect sandbox evasion techniques in malware samples by analyzing timing checks, VM artifact queries, user interaction detection, and sleep inflation patterns from Cuckoo/AnyRun behavioral reports.

marysatasselshaped667/skills-collection-1 · 46 tokens

analyzing-malware-behavior-with-cuckoo-sandbox

Detonate malware samples in Cuckoo Sandbox to observe runtime behavior — process creation, file system and registry changes, network communications, and API calls — and generate behavioral reports for classification and IOC extraction. Use when a sample has passed static triage and needs dynamic/behavioral analysis…

mukul975/Anthropic-Cybersecurity-Skills · 93 tokens

analyzing-malware-sandbox-evasion-techniques

Detect sandbox and VM evasion techniques in malware samples by analyzing timing checks, VM/hypervisor artifact queries, user-interaction checks, and sleep-inflation patterns from Cuckoo or AnyRun behavioral reports. Use when a sample shows no or minimal activity in a sandbox, when a behavioral report needs review for…

mukul975/Anthropic-Cybersecurity-Skills · 89 tokens

importing-a-codebase

Use when the repo holds real source code but no specs: the existing-codebase branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for empty workspaces (starting-a-new-project) or feature work in a specced project (brainstorming).

JetBrains/thinkrail · 69 tokens

starting-a-new-project

Use when the workspace is empty — no code yet — and the user brings a raw idea: the brand-new branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for features in an existing project — use brainstorming instead.

JetBrains/thinkrail · 61 tokens