MalChela Meets AI: Three Paths to Smarter Malware Analysis

In a previous post I wrote about integrating MalChela with OpenCode on REMnux and giving the AI a quick briefing on the tool suite so it could incorporate them into its analysis workflow. That was a promising proof of concept, but it raised a natural follow-up question: how do you make these integrations more robust, reproducible, and persistent?

Since that post, I’ve been experimenting with three different approaches to bringing MalChela into AI-assisted workflows — each suited to a different environment and use case. This post walks through all three.


Approach 1: The Kali MCP Server (Toby)

The first implementation started with Toby — my portable Raspberry Pi forensics toolkit running a customized Kali Linux build. Toby is designed for headless operation via SSH, which turns out to be exactly the right architecture for an MCP server. The developers of Kali recently added an update to support MCP integrations. (See https://www.kali.org/blog/kali-llm-claude-desktop/)

Model Context Protocol (MCP) is an open standard that allows AI assistants like Claude to interface with external tools and systems in a structured, reliable way. Instead of pasting instructions into a chat window each session, you define your tools once in a server configuration and the AI has consistent, persistent access to them.

The setup leverages an existing open-source mcp-kali-server that exposes Kali’s forensic and security tooling as MCP tools. On the client side (Mac), the claude_desktop_config.json simply points to Toby (or your Kali box) over SSH:

{
"mcpServers": {
"mcp-kali-server": {
"command": "ssh",
"args": [
"-i",
"/Users/dwmetz/.ssh/id_ed25519",
"dwmetz@192.168.10.89",
"mcp-server"
],
"transport": "stdio"
}
}
}

With this in place, Claude Desktop has persistent, session-independent access to Kali’s toolkit running on Toby. No need to re-brief the AI each session — the tools are always available and always described the same way.

Key prerequisite: passwordless SSH key-based auth between your Mac and Toby. If you haven’t set that up:

ssh-keygen -t ed25519
ssh-copy-id user@<toby/kali-ip>
# Then one manual SSH to accept the host key fingerprint
ssh user@<toby/kali-ip>

Adding MalChela to the Kali MCP Server

The mcp-kali-server ships with routes for Kali’s built-in security tools, but MalChela isn’t included out of the box. Adding it requires changes to two files: kali_server.py (the Flask API backend) and mcp_server.py (the FastMCP frontend). Both live at /usr/share/mcp-kali-server/.

How the architecture works: mcp_server.py is what Claude talks to — it defines MCP tool names, descriptions, and parameter schemas. When a tool is called, it POSTs to kali_server.py, which constructs the actual shell command and executes it on Toby. The critical detail is that MalChela’s binaries must be run from within the MalChela workspace directory — running them from an arbitrary working directory causes failures. The cd {MALCHELA_DIR} && prefix in every command handles this.

kali_server.py changes

Add the MALCHELA_DIR constant (update with your MalChela install path) and Flask routes after the existing tool routes, before the health check endpoint:

# ============================================================
# MalChela Tool Routes
# Adjust MALCHELA_DIR if MalChela is installed elsewhere
# ============================================================
MALCHELA_DIR = "/home/dwmetz/tools/MalChela"
@app.route("/api/tools/malchela/fileanalyzer", methods=["POST"])
def malchela_fileanalyzer():
"""MalChela: Hash, entropy, packing detection, PE headers, YARA scan, VirusTotal lookup."""
try:
params = request.json
filepath = params.get("filepath", "")
if not filepath:
return jsonify({"error": "filepath parameter is required"}), 400
command = f"cd {MALCHELA_DIR} && ./target/release/fileanalyzer \"{filepath}\""
result = execute_command(command)
return jsonify(result)
except Exception as e:
logger.error(f"Error in malchela_fileanalyzer endpoint: {str(e)}")
return jsonify({"error": f"Server error: {str(e)}"}), 500
@app.route("/api/tools/malchela/mstrings", methods=["POST"])
def malchela_mstrings():
"""MalChela: Extract strings, apply Sigma rules, map to MITRE ATT&CK."""
try:
params = request.json
filepath = params.get("filepath", "")
if not filepath:
return jsonify({"error": "filepath parameter is required"}), 400
command = f"cd {MALCHELA_DIR} && ./target/release/mstrings \"{filepath}\""
result = execute_command(command)
return jsonify(result)
except Exception as e:
logger.error(f"Error in malchela_mstrings endpoint: {str(e)}")
return jsonify({"error": f"Server error: {str(e)}"}), 500
@app.route("/api/tools/malchela/malhash", methods=["POST"])
def malchela_malhash():
"""MalChela: Query a hash against VirusTotal and MalwareBazaar."""
try:
params = request.json
hash_value = params.get("hash", "")
if not hash_value:
return jsonify({"error": "hash parameter is required"}), 400
command = f"cd {MALCHELA_DIR} && ./target/release/malhash \"{hash_value}\""
result = execute_command(command)
return jsonify(result)
except Exception as e:
logger.error(f"Error in malchela_malhash endpoint: {str(e)}")
return jsonify({"error": f"Server error: {str(e)}"}), 500
@app.route("/api/tools/malchela/nsrlquery", methods=["POST"])
def malchela_nsrlquery():
"""MalChela: Query file hash against NIST NSRL known-good database."""
try:
params = request.json
filepath = params.get("filepath", "")
if not filepath:
return jsonify({"error": "filepath parameter is required"}), 400
command = f"cd {MALCHELA_DIR} && ./target/release/nsrlquery \"{filepath}\""
result = execute_command(command)
return jsonify(result)
except Exception as e:
logger.error(f"Error in malchela_nsrlquery endpoint: {str(e)}")
return jsonify({"error": f"Server error: {str(e)}"}), 500
@app.route("/api/tools/malchela/hashit", methods=["POST"])
def malchela_hashit():
"""MalChela: Generate MD5, SHA1, and SHA256 hashes for a file."""
try:
params = request.json
filepath = params.get("filepath", "")
if not filepath:
return jsonify({"error": "filepath parameter is required"}), 400
command = f"cd {MALCHELA_DIR} && ./target/release/hashit \"{filepath}\""
result = execute_command(command)
return jsonify(result)
except Exception as e:
logger.error(f"Error in malchela_hashit endpoint: {str(e)}")
return jsonify({"error": f"Server error: {str(e)}"}), 500
@app.route("/api/tools/malchela/fileminer", methods=["POST"])
def malchela_fileminer():
"""MalChela: Scan a directory for file type mismatches and metadata anomalies."""
try:
params = request.json
dirpath = params.get("dirpath", "")
if not dirpath:
return jsonify({"error": "dirpath parameter is required"}), 400
command = f"cd {MALCHELA_DIR} && ./target/release/fileminer \"{dirpath}\""
result = execute_command(command)
return jsonify(result)
except Exception as e:
logger.error(f"Error in malchela_fileminer endpoint: {str(e)}")
return jsonify({"error": f"Server error: {str(e)}"}), 500

Important note on malhash: Unlike the other tools which take a file path, malhash takes a hash string as its argument. The route reads a hash parameter and passes it directly to the binary. Passing a filepath to malhash will fail silently — a subtle but critical distinction.

mcp_server.py changes

The MalChela tool definitions need to be added to the setup_mcp_server() function, immediately before the return mcp line.

    @mcp.tool(name="malchela_fileanalyzer")
    def malchela_fileanalyzer(filepath: str) -> Dict[str, Any]:
        """
        MalChela: Static file analysis - hashes, entropy, packing detection,
        PE metadata (imports, sections, timestamps), YARA matches, VirusTotal status.
        Best first step for any unknown file.

        Args:
            filepath: Absolute path to the file to analyze

        Returns:
            Analysis report
        """
        return kali_client.safe_post("api/tools/malchela/fileanalyzer", {"filepath": filepath})

    @mcp.tool(name="malchela_mstrings")
    def malchela_mstrings(filepath: str) -> Dict[str, Any]:
        """
        MalChela: String extraction with IOC detection and MITRE ATT&CK mapping.
        Applies Sigma-style detection rules, flags suspicious patterns (registry keys,
        encoded payloads, suspicious DLL+API combos), maps findings to ATT&CK techniques.

        Args:
            filepath: Absolute path to the file to analyze

        Returns:
            String analysis with ATT&CK mappings and IOCs
        """
        return kali_client.safe_post("api/tools/malchela/mstrings", {"filepath": filepath})

    @mcp.tool(name="malchela_malhash")
    def malchela_malhash(hash: str) -> Dict[str, Any]:
        """
        MalChela: Query a file hash against VirusTotal and MalwareBazaar.
        Returns detection ratio, AV verdicts, first/last seen dates, and sample metadata.
        Requires VT_API_KEY env var; MB_API_KEY optional.

        Args:
            hash: MD5, SHA1, or SHA256 hash string to query

        Returns:
            Threat intel results from VirusTotal and MalwareBazaar
        """
        return kali_client.safe_post("api/tools/malchela/malhash", {"hash": hash})

    @mcp.tool(name="malchela_hashit")
    def malchela_hashit(filepath: str) -> Dict[str, Any]:
        """
        MalChela: Generate MD5, SHA1, and SHA256 hashes for a single file.
        Lightweight when you need hashes without full fileanalyzer output.

        Args:
            filepath: Absolute path to the file

        Returns:
            File hashes
        """
        return kali_client.safe_post("api/tools/malchela/hashit", {"filepath": filepath})

    @mcp.tool(name="malchela_fileminer")
    def malchela_fileminer(folderpath: str) -> Dict[str, Any]:
        """
        MalChela: Scan a folder for file type mismatches and metadata anomalies.
        Classifies all files, flags executables disguised as other types.

        Args:
            folderpath: Absolute path to the folder to scan

        Returns:
            File classification and anomaly report
        """
        return kali_client.safe_post("api/tools/malchela/fileminer", {"dirpath": folderpath})

    return mcp

One parameter naming detail worth noting: mcp_server.py receives folderpath from Claude, but must pass it as dirpath in the JSON body to kali_server.py — that’s what the Flask route reads. The tool definition above handles this correctly.

After saving both files, restart the MCP server and restart Claude Desktop.

Testing on an unknown malware sample

[below is the exact response received from Claude]

I’ll run MalChela analysis on that file via Toby. Let me load the tools first.Tools loaded. Running fileanalyzer first for static analysis, then mstrings for IOC/ATT&CK mapping. Let me verify the path exists:File confirmed on Toby. The MalChela MCP tools use local paths — let me run it directly via the Kali execute_command since the MCP path routing doesn’t map Toby paths. I’ll invoke MalChela’s binaries directly:MalChela binaries found. Running the full suite now:That’s already very telling. Now running mstrings for IOC and ATT&CK mapping:Now let me pull the VirusTotal intel on the hash:That’s a solid picture. Here’s the full analysis breakdown:

🔴 MalChela Analysis — unknown.exe

Identification

FieldValue
SHA256dca40a0120ea176aa65b99c90d171761cb8bf696be4be026941f7f54e3c21635
MD55e364c1e35445b655ca30ab0c5bc7a4a
SHA10ac9950d00429ff4509c7fb9aa7320a45a0465ea
MalwareBazaar FilenameBL 3425005143.bat (disguised as .bat, submitted as .exe)
OriginPoland (PL), submitted anonymously
First Seen2026-03-03 13:38:42 UTC — very fresh

🧬 Verdict: GuLoader

39/69 detections on VirusTotal. Multiple vendors confirm this as GuLoader (NSIS-based downloader/injector):

  • ESET: NSIS/Injector.ENS trojan
  • Malwarebytes: Trojan.GuLoader
  • Fortinet: NSIS/Injector.7A4A!tr
  • Kaspersky: HEUR:Trojan-Downloader.Win32.Minix.gen
  • MalwareBazaar Signature: GuLoader

📦 Static Analysis Highlights

  • Entropy: 7.96 — near-maximum, strongly indicating packed/encrypted payload
  • Packer: NSIS (Nullsoft Scriptable Install System) wrapper — common GuLoader delivery vehicle
  • Compile Timestamp: 2018-12-15 (likely spoofed/stomped)
  • Unsigned — no digital signature
  • 5 PE sections including .ndata (atypical NSIS section, flagged as suspicious)
  • 159 imports, including the dangerous trio:
    • GetProcAddress / LoadLibraryExA — dynamic API resolution (evasion)
    • ShellExecuteExA — process execution

🎯 MITRE ATT&CK Mappings (from mstrings)

TechniqueIDTactic
Obfuscated Files or InformationT1027Defense Evasion
Process InjectionT1055Defense Evasion / Privilege Escalation
Application Layer Protocol: Web ProtocolsT1071.001Command and Control

🌐 Network IOC

  • http://nsis.sf.net/NSIS_Error — NSIS error handler URL (confirms NSIS wrapper), not inherently malicious but characteristic of GuLoader’s packaging

Summary

This is a live GuLoader sample — an NSIS-wrapped shellcode injector/downloader commonly used as a first-stage payload to retrieve second-stage malware (often AgentTesla, Remcos RAT, FormBook, etc.). The high entropy, dynamic API loading, and process injection indicators are all consistent with GuLoader’s known behavior. Treat this as active malware — do not execute outside an isolated sandbox.


Approach 2: Persistent MalChela Instructions in OpenCode on REMnux

The REMnux OpenCode integration I described in the previous post worked, but it had one friction point: each new session required re-pasting the MalChela context. OpenCode has a solution for this — the AGENTS.md file.

Place an AGENTS.md file in your working directory (or MalChela’s root directory) and OpenCode will automatically load it as persistent context for every session started from that location. This is the most lightweight way to make MalChela tool-aware without building any infrastructure.

Create the file at /home/remnux/Tools/MalChela/AGENTS.md:

# MalChela Tool Instructions for AI Assistants
MalChela is installed at: /home/remnux/Tools/MalChela
All tools are Rust binaries. The execution pattern is:
cd /home/remnux/Tools/MalChela
./target/release/<toolname> <arguments>
## Primary Static Analysis Tools
| Tool | Binary | Description |
|------|--------|-------------|
| File Analyzer | fileanalyzer | Hash, entropy, packing detection, PE info, YARA scan, VirusTotal lookup |
| mStrings | mstrings | String extraction, Sigma rule matching, Regex, MITRE ATT&CK mapping |
| NSRL Hash Lookup | nsrlquery | Query MD5/SHA1 against the NIST NSRL known-good database |
| Malware Hash Lookup | malhash | Query a hash against VirusTotal and MalwareBazaar |
## Additional Tools
| Tool | Binary | Description |
|------|--------|-------------|
| File Miner | fileminer | Scan directories for file type mismatches and metadata anomalies |
| Hash It | hashit | Generate MD5, SHA1, and SHA256 for a single file |
| mzHash | mzhash | Recursively hash all files in a directory |
| Extract Samples | extract_samples | Extract files from password-protected malware archives |
## Recommended Workflow
For initial triage of an unknown file:
1. fileanalyzer - establish baseline: hashes, entropy, PE headers
2. mstrings - extract strings, look for IOCs and ATT&CK technique indicators
3. malhash - check community threat intelligence
4. nsrlquery - confirm or rule out known-good status
## Environment Notes
- API keys (VT_API_KEY, MB_API_KEY) should be set in the shell environment
- MalChela integrates with REMnux tools; use REMnux CLI tools in conjunction as needed
- Case management is available via the MalChela GUI if a graphical session is active

When you start an OpenCode session from the MalChela directory, this context is automatically loaded. No manual pasting, no re-briefing.

Once complete I asked it to save the results to the Desktop in markdown.

What was cool to me about this approach is that using the installed REMnux tools, you can take the analysis further after MalChela. In my testing I (OpenCode) analyzed a file with mStrings. We then followed up by running capa against the file. From there we could compare what each tool detected and missed in the sample. (screenshot truncated)


Approach 3: MalChela as a Native MCP Server (Mac)

The most powerful integration is running MalChela as its own dedicated MCP server — making its tools directly available to Claude Desktop alongside the Kali server. This is what we built out as mcp-malchela.

The server is a small Node.js project that wraps MalChela’s binaries with proper MCP tool definitions. The key files are index.js (the server logic) and package.json.

package.json:

{
"name": "mcp-malchela",
"version": "1.0.0",
"description": "MCP server exposing MalChela malware analysis tools",
"main": "index.js",
"dependencies": {
"@modelcontextprotocol/sdk": "^1.0.0"
}
}

index.js — the server defines each MalChela tool with its input schema, executes the binary when called, and streams back results. Note that malhash is handled differently from the other tools — it receives a hash string rather than a filepath, so the argument routing accounts for that explicitly:

import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { CallToolRequestSchema, ListToolsRequestSchema } from "@modelcontextprotocol/sdk/types.js";
import { execSync } from "child_process";
import path from "path";
const MALCHELA_DIR = process.env.MALCHELA_DIR || "/Users/dmetz/GitHub/MalChela";
const RELEASE_DIR = path.join(MALCHELA_DIR, "target", "release");
const server = new Server(
{ name: "mcp-malchela", version: "1.0.0" },
{ capabilities: { tools: {} } }
);
const tools = [
{
name: "malchela_fileanalyzer",
description: "Analyze a file: hashes, entropy, packing detection, PE headers, YARA scan, VirusTotal lookup",
inputSchema: {
type: "object",
properties: {
filepath: { type: "string", description: "Absolute path to the file to analyze" }
},
required: ["filepath"]
}
},
{
name: "malchela_mstrings",
description: "Extract strings from a file, apply Sigma rules and Regex patterns, map to MITRE ATT&CK",
inputSchema: {
type: "object",
properties: {
filepath: { type: "string", description: "Absolute path to the file to analyze" }
},
required: ["filepath"]
}
},
{
name: "malchela_malhash",
description: "Query a hash against VirusTotal and MalwareBazaar",
inputSchema: {
type: "object",
properties: {
hash: { type: "string", description: "MD5, SHA1, or SHA256 hash string to query" }
},
required: ["hash"]
}
},
{
name: "malchela_nsrlquery",
description: "Query a file hash against the NIST NSRL known-good database",
inputSchema: {
type: "object",
properties: {
filepath: { type: "string", description: "Absolute path to the file to query" }
},
required: ["filepath"]
}
}
];
server.setRequestHandler(ListToolsRequestSchema, async () => ({ tools }));
server.setRequestHandler(CallToolRequestSchema, async (request) => {
const { name, arguments: args } = request.params;
const env = { ...process.env };
const binaryMap = {
malchela_fileanalyzer: "fileanalyzer",
malchela_mstrings: "mstrings",
malchela_malhash: "malhash",
malchela_nsrlquery: "nsrlquery"
};
const binary = binaryMap[name];
if (!binary) throw new Error(`Unknown tool: ${name}`);
// malhash takes a hash string; all other tools take a filepath
const arg = name === "malchela_malhash" ? args.hash : args.filepath;
const cmd = `cd "${MALCHELA_DIR}" && ./target/release/${binary} "${arg}"`;
try {
const output = execSync(cmd, { env, encoding: "utf8", maxBuffer: 10 * 1024 * 1024 });
return { content: [{ type: "text", text: output }] };
} catch (error) {
return { content: [{ type: "text", text: error.stdout || error.message }] };
}
});
const transport = new StdioServerTransport();
await server.connect(transport);

Setup:

mkdir ~/mcp-malchela
cd ~/mcp-malchela
# create index.js and package.json as above
npm install

claude_desktop_config.json — with both servers configured:

{
"mcpServers": {
"mcp-kali-server": {
"command": "ssh",
"args": [
"-i",
"/Users/dwmetz/.ssh/id_ed25519",
"dwmetz@192.168.10.89",
"mcp-server"
],
"transport": "stdio"
},
"malchela": {
"command": "node",
"args": ["/Users/dmetz/mcp-malchela/index.js"],
"env": {
"MALCHELA_DIR": "/Users/dmetz/Tools/MalChela"
}
}
}
}

Restart Claude Desktop and both MCP servers will be active and available in every session.


I'll load the MalChela tools and run analysis on that file on your Mac.
Searched available tools
Starting with fileanalyzer for the full static analysis pass.
Fileanalyzer
VirusTotal flags it as malicious. Let me pull the full VT/MalwareBazaar intel and then run strings analysis.
Malhash
Confirmed SalatStealer. Let me run strings analysis to surface IOCs and ATT&CK mappings.
Ran 5 commands, used malchela integration
That's a solid picture. Here's the full breakdown:

🔴 unknown3.exe — SalatStealer (Confirmed Malicious)

Identity

FieldValue
SHA256e0c90f401ae5d23a551f2d75a826cec7f187a6b7f0da2d24565c880e027ae9a3
MD5cfcd64360a0b0c3185f9a48b1dbe1bdc
FamilySalatStealer (Trojan.PWS.Salat)
VT Detections33/68 — confirmed malicious
First Seen2026-03-03 15:37 UTC (very fresh)
OriginNL (Netherlands), reported by abuse.ch
LanguageGo (Golang) — evident from stdlib and module paths
Architecturei386 (32-bit PE)
PackerUPX (MalwareBazaar notes this is the UPX-decompressed form; original packed SHA256: 30a50cc0f7...)
Code SigningAbsent
Compile TimestampEpoch zero (1970-01-01) — deliberately zeroed/spoofed

MITRE ATT&CK Coverage (11 Techniques)

TechniqueIDWhat was found
Obfuscated Files / PackingT1027DOS stub + packer artifact
OS Credential Dumping (LSASS)T1003.001String matches
WMI Execution/DiscoveryT1047ffwmic reference
Process InjectionT1055Injection-capable imports
Scripting InterpreterT1059JSON/script interpreter refs
Web Protocol C2T1071.001WebSocket + HTTP/2 libs, hardcoded domains
System Info DiscoveryT1082System enumeration strings
File & Dir DiscoveryT1083File path enumeration
Ingress Tool TransferT1105Download capability
Unsecured CredentialsT1552passwordusernameloginPBEpasswordSet

Notable IOCs from Strings

  • Clients\DiscordTokens.txt — Discord token harvesting
  • moz_cookies SQL query — Firefox cookie theft
  • yandexbrowser — Yandex Browser credential targeting
  • *main.loginPBE — Login/credential parsing function
  • WebSocket C2 comms — *websocket.netDialerFunc*websocket.netError
  • WMI usage — likely for system enumeration pre-exfil

Bottom Line

This is a Go-compiled password/credential stealer targeting browsers (Firefox cookies, Discord tokens, Yandex Browser), using WebSocket for C2, with WMI-based discovery. It was UPX-packed (this is the unpacked copy), has a zeroed compile timestamp to defeat timestamp-based triage, and was submitted to MalwareBazaar just hours ago — very fresh sample. Do not execute in any environment without proper isolation.

VT permalink for full AV breakdown: https://www.virustotal.com/gui/file/e0c90f401ae5d23a551f2d75a826cec7f187a6b7f0da2d24565c880e027ae9a3/detection


Comparing the Three Approaches

Kali MCP (Toby)OpenCode AGENTS.mdMalChela MCP
PlatformKali (Raspberry Pi)REMnuxmacOS
PersistenceFull (MCP server definition)Full (file-based)Full (MCP server definition)
Setup complexityMedium (SSH + server install + file edits)Low (one markdown file)Medium (Node.js server)
AI integration depthStructured tool callsNatural language with contextStructured tool calls
Best forField analysis with TobyREMnux-primary workflowsMac-based analysis with MalChela

All three approaches solve the same core problem from the original post: making the AI reliably aware of your tools without re-briefing it every session. The right choice depends on your primary analysis environment — or, if you’re like me, you end up running all three.


All of the configuration files discussed here — including the MCP server setup and the are available in the MalChela repository on GitHub. Clone or pull the latest and you should be ready to go. As always, if you run into issues or have ideas for where to take the MCP integration next, open an issue or drop me a note.

2025 Year in Review: Open Source DFIR Tools and Malware Analysis Projects

As 2025 draws to a close, I’m taking a moment to reflect on what turned out to be one of my most productive years in code. From major releases to entirely new projects, this year saw significant evolution across my DFIR toolkit—driven by real-world incident response needs, classroom teaching experiences, and late-night tinkering sessions fueled by good bourbon and better puzzles.

What started as continuing work on CyberPipe evolved into a year of substantial innovation: creating MalChela for YARA and malware analysis, building a portable Raspberry Pi forensics platform, developing automated timeline generation workflows, and crafting specialized utilities that solve specific problems I encountered in the field. Each tool represents not just lines of code, but practical solutions to challenges that digital forensics and incident response professionals face daily.

Whether you’re a seasoned forensic analyst, an incident responder building your toolkit, or a student just getting started in DFIR, my hope is that these open-source projects make your work a little easier and a lot more efficient. All tools remain freely available on GitHub, because I believe the best way to advance our field is to share knowledge and capabilities openly.

Here’s what kept me busy in 2025:

MalChela – YARA & Malware Analysis Toolkit (Rust)

My flagship project that evolved significantly throughout 2025:

  • March: Initial release – Combined 10 programs into one Rust workspace for YARA and malware analysis
  • May: v2.1 – Added smoother workflows, better third-party tool integration, and enhanced argument handling
  • May: v2.2 “REMnux Release” – Native support for REMnux, integrations with Volatility3, Tshark, YARA-X
  • June: v3.0 – Major update introducing Case Management system, FileMiner (replacing MismatchMiner), and tool suggestion capabilities based on file characteristics
  • July: v3.0.1 – Refinements to mStrings, improved MITRE mappings, “Select All” functionality, optimizations for running on Toby
  • August: v3.0.2 – Enhanced threat hunting with MITRE ATT&CK technique lookup

MalChela at a Glance

  • Rust-based malware analysis toolkit combining YARA scanning, file analysis, hash generation, string extraction with MITRE ATT&CK mapping, and automated malware sample extraction from password-protected archives 
  • Multiple specialized utilities including mzhash/xmzhash for corpus generation, file type mismatch detection, entropy analysis, PE structure examination, and fuzzy hashing capabilities 
  • Integrated threat intelligence with VirusTotal and Malware Bazaar API support, NSRL database queries for known-good file filtering, and Sigma rule application for IOC identification 
  • Case management system (v3.0) featuring unified tracking of files, tools, and notes in case.yaml format with auto-saved outputs, tagging, search functionality, and VS Code integration 
  • Extensible architecture supporting custom tool integration via tools.yamlconfiguration, enhanced support for Volatility 3, TShark, and YARA-X, with both GUI and CLI modes (WSL2-compatible on Windows)
  • Complete documentation embedded as PDF or online

https://github.com/dwmetz/MalChela

CyberPipe – Incident Response Collection Tool (PowerShell)

Continued evolution of the enterprise digital evidence collection script:

  • May: v5.1 – Streamlined profiles with better flexibility, customizable collection profiles
  • October: v5.2 – Improved collection methods with dual disk space validation, SHA-256 hashing of artifacts, single-file reporting, network collection simplification
  • November: v5.3 – Critical PowerShell 5.1 compatibility fixes, dual validation logic, enhanced reliability across all PowerShell environments

https://github.com/dwmetz/CyberPipe

CyberPipe-Timeliner ✱New✱ (PowerShell)

  • NovemberCyberPipe-Timeliner – New companion project to CyberPipe that automates the workflow from Magnet Response collections to unified forensic timelines using Eric Zimmerman’s EZ Tools and ForensicTimeliner

https://github.com/dwmetz/CyberPipe-Timeliner

Toby – Portable Raspberry Pi Forensics Toolkit

  • July: Released Toby – A compact forensics toolkit built on Raspberry Pi Zero 2 W running customized Kali Linux, designed for headless operation via SSH/VNC, perfect for field analysis and malware triage

Toby-Find

  • JulyToby-Find – Terminal-based command-line helper tool for discovering CLI forensics tools in KALI and REMnux environments, created initially for university teaching

https://github.com/dwmetz/Toby

Crabwise – USB Device Benchmark Utility (Rust)

  • August: Released Crabwise – A lightweight USB benchmarking tool that measures true read/write speeds of USB devices for forensic workflows. Tests write throughput with pseudo-random data and read performance under uncached conditions. Includes logging functionality to track performance across different cables, hubs, and connection paths, helping forensic investigators optimize their hardware setups.

https://github.com/dwmetz/Crabwise

Toolbox Utilities – Specialized Python and Bash Scripts

Standalone tools maintained in the Toolbox repository:

  • OctoberCoreBreaker.py – Breaks large yara-rules-core files into smaller .yar files for tool ingestion
  • OctoberEtTu.py – Caesar cipher brute force decoder (created for Murdle puzzle solving); After all, All work and no play makes Jack a dull boy.
  • Novembercloudtrail_timeline.py – Parses AWS CloudTrail JSON logs and outputs CSV format for Timeline Explorer
  • Novembermac_triage_timeline.sh – Processes Mac-Triage ZIP files and generates timeline for Timeline Explorer
  • Novemberuac_timeline.sh – Processes UAC tar.gz files and generates timeline for Timeline Explorer (Linux/macOS)

https://github.com/dwmetz/Toolbox


All projects are available on my GitHub at github.com/dwmetz, with detailed documentation on bakerstreetforensics.com. My goal is making DFIR and malware analysis more accessible, automated, and efficient for incident responders and forensic analysts.

Toby-Find: Simplifying Command-Line Forensics Tools

In digital forensics, we often take a toolbox approach — success hinges on having the right tool for the job. Some tools offer broad functionality, while others are deeply specialized. Distributions like KALI and REMnux do a fantastic job bundling a wide range of forensic and security tools, but keeping track of what’s actually installed can be a challenge.

If you’re using a graphical interface, browsing through available packages is fairly intuitive. But when you’re living in the terminal — as many analysts do — that discoverability disappears. There’s no built-in index of command-line tools or how to invoke them.

The first version of Toby-Find was born out of necessity. I teach a Network Forensics course at the university, using a custom VM loaded with tools like Zeek, Tshark, Suricata, and more. I wanted students to have an easy, searchable way to see what CLI tools were available and how to run them — without needing to memorize commands or dig through man pages.

Later, when I built Toby (a forensic-focused Raspberry Pi rig running a customized KALI install), I updated Toby-Find to include the complete CLI toolset geared toward forensics and malware analysis from the KALI ecosystem.

And because I can’t leave well enough alone, I decided to build a REMnux-compatible version too.

Once installed, you can launch Toby-Find (via tf, toby-find, or tf-help) from any terminal and instantly search for tools, descriptions, examples, and more.

Toby-Find on REMnux
Toby-Find on Kali

📦 Installation

1. Clone the repository:

git clone https://github.com/dwmetz/Toby.git

2. Make the install script executable:

cd Toby
chmod +x install.sh

3. Run the installer:

./install.sh

4. Follow the prompt to choose your environment (KALI or REMnux)
5. Open a new terminal or run:

source ~/.bashrc   # or ~/.zshrc depending on shell

🚀 Usage

tf [keyword]

Examples:

tf yara
tf volatility
tf hash

To view the full list:

tf-help

Whether you’re working from a custom VM, a rugged Pi, or a hardened REMnux box, Toby-Find gives you a fast, terminal-friendly way to surface the tools at your disposal — without breaking focus. It’s lightweight, portable, and easy to extend for your own lab or classroom.

You can grab the full installer from GitHub, and contributions are always welcome. If you find it helpful — or build on it — I’d love to hear about it.


Portable Forensics with Toby: A Raspberry Pi Toolkit

Whether teaching, investigating, or tinkering on the road, there’s an undeniable appeal to a device that’s self-contained, headless, and versatile enough to support forensic analysis, malware triage, and field acquisition. That idea became the seed for Toby — a Raspberry Pi Zero 2 W–based micro-rig that can be managed from an iPad or mobile device.

It started off with a “what could I do with at Raspberry Pi” and the final result: a fully functional, go-anywhere forensics toolkit that fits in the palm of your hand, carefully packed into a Grid-It travel kit and loaded with purpose.


Why Build Toby?

Toby wasn’t born from necessity. It came from a blend of curiosity, constraint, and the spirit of joyful overengineering. The goal wasn’t just to get Kali Linux running on a Pi — that’s been done. The challenge was in how much capability could be packed into a minimalist footprint without compromising on control, security, or style.

Some driving goals from the outset:

  • Headless-first: Must be operable via SSH, or VNC — no screen needed.
  • Kali-based: Full access to familiar forensic and pentest tooling.
  • Discreet and functional: Everything should be secure, practical, and stowable.
  • Modular connectivity: USB OTG, video capture, remote keyboard/mouse, and VPN support all needed to be viable.
  • Portable power: Run from a battery pack for field ops or demo use without dependency on AC power.

Hardware Selection

Raspberry Pi Zero 2 W

The Pi Zero 2 W hits a sweet spot. It has enough power to run full Kali and perform triage analysis, especially with swap and careful headless tuning. It supports USB OTG and can be powered over micro-USB, making it ideal for lightweight builds.

Grid-It Travel Kit: The Physical Layout

Instead of housing the components in a fixed enclosure, I opted for flexibility: a Grid-It organizer sleeve. It allows each cable and tool to remain accessible and secured via elastic straps — perfect for quick swaps or field reconfiguration.

The current loadout includes:

  • Raspberry Pi Zero 2 W 
  • HDMI mini to full adapter (for display recovery if needed)
  • USB micro to USB-C adapter combo (for powering Pi from laptop, iPad, or battery pack)
  • Anker battery pack (portable, long runtime)
  • Wireless keyboard (compact; paired via Bluetooth or USB receiver)
  • USB capture device (used for teaching, demoing webcam/VNC sessions)
  • Short USB OTG cable

The setup is light, self-contained, and TSA-friendly — a true digital go-bag for the forensically inclined.


Portable Power

Toby can be powered from the USB port of an iPad or from a battery pack or AC adapter, making it extremely flexible for field use.

Toby powered from iPad Pro
Toby powered from portable battery

Software

The OS is a clean, headless Kali Linux image configured specifically for ARM on the Pi Zero 2 W. Rather than trying to turn it into a desktop experience (even though it can), it boots fast, runs lean, and drops me directly into a terminal where I can get to work — whether over SSH or local keyboard.

Core Components:

Base image: Raspbian (Debian-based) with Kali tools manually installed

Metapackages:

  • kali-linux-forensic
  • kali-linux-desktop
  • core/default Kali utilities and command-line tools, incrementally layered until the system was functionally equivalent to a full Kali install (minus unnecessary services)

Additional Software Intstalled:

MalChela (CLI) running on Toby
Kali Forensics tools on Toby
MalChela GUI running on Toby

🔍 Toby-find: Your On-Device Forensics Cheat Sheet

One of Toby’s handiest features isn’t a tool you run—it’s a tool to remember tools. toby-find is a simple but powerful command-line helper built into the system. It gives you fast access to a curated list of CLI forensics tools available on Toby, along with short descriptions and usage tips.

It’s like having a searchable cheat sheet, always available—perfect for field use when memory is fuzzy or connectivity is limited.

toby-find utility

What It Does

When you run:

toby-find [keyword] 

it will search the help file for any tool(s) mentioning the keyword in name or description, and provide back a simple command syntax for each tool.

Example:

dwmetz@toby:~$ toby-find strings

Tool:        mstrings
Description: Extracts printable strings from files and maps them to MITRE ATT&CK techniques.
Example:     mstrings suspicious.exe
Category:    Malware
--------------------------------------------------
Tool:        strings_to_yara
Description: Generates a basic YARA rule from strings gathered manually or via mstrings.
Example:     strings_to_yara
Category:    Malware
--------------------------------------------------
Tool:        floss
Description: Extracts obfuscated strings from malware binaries.
Example:     floss suspicious.exe
Category:    Forensics
--------------------------------------------------
Tool:        rephrase
Description: Analyzes and reformats strings from documents or binaries.
Example:     rephrase input.txt
Category:    Forensics
--------------------------------------------------

Installed Tools:

Many of the tools are native to Kali, but some, including MalChela, were compiled manually or added through custom scripts. (Bold == MalChela tools or custom scripts.)

Tool NameDescription
batCat replacement with syntax highlighting and Git integration.
binwalkScans binaries for embedded files and executable code.
bulk_extractorExtracts artifacts like emails and credit card numbers from disk images.
combine_yaraCombines multiple YARA rule files into a single merged rule set.
dffDigital Forensics Framework with CLI and GUI modes.
digPerforms DNS lookups to retrieve domain IPs and records.
exiftoolDisplays metadata from images, PDFs, and other file types.
extract_samplesExtracts files from password-protected ZIP and RAR archives.
fileanalyzerAnalyzes file metadata, headers, and hashes to assist triage and detection.
fileminerRecursively scans a directory for files of interest based on extensions and type.
flossExtracts obfuscated strings from malware binaries.
foremostRecovers deleted files from disk images using file carving.
hashcheckComputes multiple cryptographic hashes and prints them side-by-side.
hashdeepGenerates and verifies file hashes for entire directories.
hashitQuickly generate MD5, SHA1, SHA256, and SHA512 hashes of a file.
htopInteractive system monitor showing real-time process usage.
ipcalcPerforms subnet calculations for IP ranges.
ipstatusShows interface configuration and public IP address.
malchelaMain CLI launcher for the MalChela forensic toolkit, with a menu-driven interface.
malhashLooks up file hashes using VirusTotal and MalwareBazaar.
moshSSH replacement that maintains session state during roaming.
mstringsExtracts printable strings from files and maps them to MITRE ATT&CK techniques.
mzcountTallies file extensions and MIME types in a directory.
mzhashRecursively hash all files in a directory using MD5.
ncduDisk usage analyzer with an interactive interface.
nmapPerforms host discovery and port scanning on a network.
nsrlqueryChecks file hashes against the National Software Reference Library.
p0fPerforms passive OS fingerprinting from live network traffic.
reglookupQueries Windows Registry hives from the command line.
regripperExtracts and parses registry artifacts using Perl-based plugins.
rephraseAnalyzes and reformats strings from documents or binaries.
rifiuti2Parses Windows Recycle Bin INFO2 files for forensic analysis.
rkhunterScans the system for known rootkits and suspicious behavior.
rsakeyfindSearches RAM dumps for RSA private key patterns.
safecopyRecovers data from damaged or unstable storage media.
samdump2Extracts password hashes from Windows SAM files.
scalpelPerforms file carving on disk images using headers/footers.
screenTerminal window manager similar to tmux.
scrounge-ntfsRecovers deleted files from NTFS file systems.
speedPerforms a network speed test from the command line.
sshStandard secure shell for remote command-line access.
ssdeepPerforms context-triggered piecewise hashing (fuzzy hashing).
strings_to_yaraGenerates a basic YARA rule from strings gathered manually or via mstrings.
tcpdumpCaptures and displays raw network packets in real time.
tmuxTerminal multiplexer for managing multiple sessions.
toby-findLists available tools and examples installed on the Toby system.
truecrackAttempts to brute-force passwords for TrueCrypt volumes.
tsharkTerminal version of Wireshark for packet capture and filtering.
undbxExtracts messages from Outlook Express DBX mailboxes.
unarExtracts files from .rar and other archives.
unhideDetects hidden processes and tasks in Linux systems.
upxCompresses or decompresses executable files.
uptimeDisplays system uptime and load averages.
vinettoParses thumbnail caches from Internet Explorer and Firefox.
vnc-offStops the running VNC session.
vnc-onStarts a VNC server session for remote desktop access.
volatility3Memory forensics framework for analyzing RAM dumps.
vpn-offStops the active OpenVPN session.
vpn-onStarts the OpenVPN client using the configured lab connection.
winregfsMounts Windows Registry hives as a read-only virtual filesystem.
xmountConverts between forensic image formats (e.g. EWF to RAW).
xmzhashRecursively hash all files in a directory using MD5, SHA1, and SHA256.

This setup enables lightweight static analysis, file triage, memory inspection, and network capture — all from a Pi that fits in a Altoids case.


Build Process (Step by Step)

1. Flashing and First Boot

Using the Raspberry Pi Imager, I selected the ARM64 Raspbian image, added SSH and Wi-Fi credentials, and flashed the SD card.

Tip: The “advanced” options in Raspberry Pi Imager let you configure headless behavior up front, saving time on first boot.

2. Swap, Networking, and System Setup

The Pi Zero 2 W is modest on RAM — just 512MB — so swap is essential. I configured a persistent 2GB file-based swap at /swapfile, which gave the system enough breathing room to compile, run heavier tools, and avoid out-of-memory crashes during extended sessions.

Networking is Wi-Fi-only, so multiple SSIDs were configured using wpa_supplicant.conf for home and hotspot SSIDs. VPN has also been configured for remote access to my home malware lab.

3. Building and Installing MalChela

I cloned the full MalChela repository directly and compiled tool-by-tool:

cd MalChela
for tool in fileanalyzer mstrings hashcheck extract_samples ...; do
  cargo build --release -p $tool
done

4. Screen Choices

In addition to headless-mode, you can use a typical keyboard/monitor/mouse setup, for either cli mode or full gui.

The Pi Zero 2 W supports HDMI output via its mini-HDMI port, so you can plug it directly into any monitor or TV using a mini-HDMI to HDMI cable or adapter. For true portability, I needed something more flexible that didn’t require me packing a separate screen.

Toby running in desktop mode

To solve this, I added a compact USB-based HDMI capture device to the kit. It effectively turns any mobile device into a live monitor. By connecting Toby’s HDMI out to the capture card and plugging it into my iPad or iPhone,  I can preview the Pi’s screen on the go. This setup also works with OBS, QuickTime, or dedicated capture apps for recording demos or screen sessions — handy for teaching or documenting tool usage.

Input is handled with a small wireless Bluetooth keyboard, which pairs cleanly with Toby for direct control. This combo — Pi output through HDMI capture and keyboard input via Bluetooth — lets me interact with Toby completely untethered.

In practice, I rarely need the GUI. But when I do, this setup lets me bring it up quickly without dragging along a dedicated screen.


Final Result: What Toby Can Do

Toby isn’t just a cute Pi rig with a name. It’s a real tool, and its current feature set reflects that.

💼 Mobile Forensics Platform

  • Mount, triage, and scan USB drives with fileanalyzer
  • Run YARA scans and generate custom rules from strings
  • Look up hashes via VirusTotal, MalwareBazaar, and NSRL
  • Analyze memory dumps with Volatility 3 (including plugin selection)
  • Run offline IOCs scans via mstrings or custom shell scripts

What’s Next for Toby

Building Toby was an exercise in maximizing power in a small footprint through deliberate choices. For educators, students, and curious tinkerers, Toby proves that hands-on, portable, and fun learning and teaching forensics can be achieved. If you’re building your own, start with what you have: a Pi, a Grid-It, and your imagination. Sometimes, the best tools aren’t the ones with the biggest screens or fastest chips—they’re the ones you have with you.

I’m already thinking about upgrades. One in consideration is a case upgrade, a true lunchbox-style metal enclosure — something retro and rugged, with a small screen inside the lid.

Let me know in the comments if you’d like a public release of toby-find as an add-on to install for Kali builds for forensics and malware analysis.