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.

Enhancing Malware Analysis with REMnux and AI

Those familiar with my work know that I’m a big fan of the REMnux Linux distribution for malware analysis. When I developed MalChela, I included a custom configuration that can be invoked that not only includes the MalChela tool suite but also integrates many of the CLI tools installed in REMnux, providing an easy-to-use GUI.

Recently, a new REMnux release was released on Ubuntu 24.04. This was a welcome upgrade because REMnux was previously locked to 20.04, which was becoming outdated. As soon as I noticed the release announcement, I downloaded the latest version and installed the MalChela suite. Everything ran smoothly, and the GUI interface even appeared slightly sharper without any changes on my part.

While reviewing the release notes for the new version, I discovered that REMnux now includes integration with Opencode AI. In REMnux, several models are preconfigured to recognize the tools included in the distribution and their capabilities and syntax. You can use natural language prompts, and the system will interpret the request, execute the appropriate tools against the file, and provide a summary of the results. As mentioned in the documentation:

The AI uses the REMnux MCP server to run the appropriate REMnux tools automatically. The MCP server offers guidance regarding the tools that the AI should consider, but it’s up to the AI agent to decide on the analysis workflow. And, of course, your interactions, requests, and observations can also direct the AI regarding the analysis steps.

Key capabilities available to AI assistants through the REMnux MCP server:

  • Analyze files based on detected type (PE, PDF, Office docs, scripts, ELF, etc.)
  • Get tool recommendations for a specific file without running them
  • Run specific REMnux tools directly, including piped commands
  • Extract indicators of compromise (IOCs) from text
  • Get usage help for any installed REMnux tool

I experimented with a few of the usual suspects in my corpus and provided pretty generic prompts like “analyze (file-xyz)” and “what are the IOCs?” The results were very positive – but I’ve only scratched the surface in testing.

Then I decided to see how adaptive this AI was and how easy it would be to make it aware of new tools and syntax. I provided the following:


MalChela tool suite is  installed in /home/remnux/Tools/MalChela
All are rust based tools so cd to the MalChela directory, and then ./target/release/fileanalyzer (path to executable) would be the syntax. 
The 4 tools below are the primary tools for static analysis.
  File Analyzer       |  Get the hash, entropy, packing, PE info, YARA and VT match status for a file  
  mStrings            |  Analyzes files with Sigma rules (YAML), extracts strings, matches ReGex. 
  NSRL Hash Lookup    |  Query an MD5 or SHA1 hash against NSRL
  Malware Hash Lookup |  Query a hash value against VirusTotal & Malware Bazaar 

Immediately it began running the tools in MalChela against the malware file I was previously analyzing and provided a summary of the different tool results.

I plan to do a lot more testing but so far things are looking very promising.

So what do you think? Are you using AI in your malware analysis workflows? What capabilities of AI do you think are most useful when it comes to malware analysis? Let me know in the comments.

MalChela 2.2 “REMnux” Release

MalChela’s 2.2 update is packed with practical and platform-friendly improvements. It includes native support for REMnux, better tool settings, and deeper integrations with analysis tools like YARA-X, Tshark, Volatility3, and the newly improved fileanalyzer module.

🦀 REMnux Edition: Built-In Support, Zero Tweaks

When the GUI loads a REMnux-specific tools.yaml profile, it enters REMnux mode.

Screenshot of yaml configuration applying REMnux mode

Native binaries and Python scripts like capa, oledump.py, olevba, and FLOSS are loaded into the MalChela tools menu, allowing you to mix and match operations with the embedded MalChela utilities and the full REMnux tool stack. No manual configuration needed—just launch and go. MalChela currently supports the following REMnux programs right out of the box:

Tool Name Description
binwalkFirmware analysis and extraction tool
capaIdentifies capabilities in executable files
radare2Advanced reverse engineering framework
Volatility 3Memory forensics framework for RAM analysis
exiftoolExtracts metadata from images, documents, and more
TSharkTerminal-based network packet analyzer (Wireshark CLI)
mraptorDetects malicious macros in Office documents
oledumpParses OLE files and embedded streams
oleidIdentifies features in OLE files that may indicate threats
olevbaExtracts and analyzes VBA macros from Office files
rtfobjExtracts embedded objects from RTF documents
zipdumpInspects contents of ZIP files, including suspicious payloads
pdf-parserAnalyzes structure and contents of suspicious PDFs
FLOSSReveals obfuscated and decoded strings in binaries
clamscanOn-demand virus scanner using ClamAV engine
stringsExtracts printable strings from binary files
YARA-XNext-generation high-performance YARA rule scanner

If you only need a subset of tools you can easily save and restore that a custom profile.


TShark Panel with Built-In Reference

Tshark and the integrated field reference

A new TShark integration exposes features including:

  • A filter builder panel
  • Commonly used fields reference
  • Tooltip hints for each example (e.g., `ip.addr == 192.168.1.1` shows “Any traffic to or from 192.168.1.1”)
  • One-click copy support

This helps analysts build and understand filters quickly—even if TShark isn’t something they use every day. Using the syntax builder in MalChela you can use the exact commands directly in Tshark or Wireshark.


YARA-X Support (Install Guide Included)

YARA-X module in MalChela

Support for YARA-X (via the `yr` binary) is now built in. YARA-X is not bundled with REMnux by default, but install instructions are included in the User Guide for both macOS and Linux users.

Once installed, MalChela allows for rule-based scanning from the GUI,and with YARA-X, it’s faster than ever.


fileanalyzer: Fuzzy Hashing, PE Metadata, and More

Updated FileAnalyzer Module

MalChela’s fileanalyzer tool has also been updated to include:

  • Fuzzy hashing support via `ssdeep`
  • BLAKE3 hashing for fast, secure fingerprints
  • Expanded PE analysis, including:
  • Import and Export Table parsing (list of imported and exported functions)
  • Compilation Timestamp (for detection of suspicious or forged build times)
  • Section Characteristics (flags like IMAGE_SCN_MEM_EXECUTE, IMAGE_SCN_CNT_CODE, etc., for detecting anomalous sections)

These improvements provide deeper insight into executable structure, helping analysts detect anomalies such as packers, suspicious timestamps, or unexpected imports/exports. Useful for everything from sample triage to correlation, fileanalyzer now digs deeper—without slowing down.


Memory Forensics Gets a Boost: Volatility 3 Now Supported

With the 2.2 release, MalChela introduces support for Volatility 3, the modern Python-based memory forensics framework. Whether you’re running MalChela in REMnux or on a customized macOS or Linux setup, you can now access the full power of Volatility directly from the MalChela GUI.

Volatility 3 in MalChela

There’s an intuitive plugin selector that dynamically adjusts available arguments based on your chosen plugin,. You can search, sort, and browse available plugins, and even toggle output options like –dump-dir with ease.

Like Tshark, there is an added plugin reference panel with searchable descriptions and argument overviews — a real time-saver when navigating Volatility’s deep and often complex toolset.

Volatility Plugin Reference

Smarter Tool Configuration via YAML

The tool configuration system continues to evolve:

  • Tools now declare their input type (file, folder, or hash)
  • The GUI dynamically adjusts the interface to match
  • Alternate profiles (like REMnux setups) can be managed simply by swapping `tools.yaml` files via the GUI
  • Easily backup or restore your custom setups
  • Restore the default toolset to get back to basics

This structure helps keep things clean—whether you’re testing, teaching, or deploying in a lab environment.


Embedded Documentation Access

The GUI now includes a link to the full MalChela User Guide in PDF. You can also access the documentation online.

From tool usage and CLI flags to configuration tips and install steps, it’s all just a click away—especially useful in offline environments or when onboarding new analysts. I’ll be honest, this is likely the most comprehensive user guide I’ve ever written.


Whether you’re reviewing binaries, building hash sets, or exploring network captures—MalChela 2.2 is designed bring together the tools you need, and make it easier to interoperate between them.

The new REMnux mode makes it even easier to get up and running with dozens of third party integrations.

Have an idea for a feature or application you’d like to see supported — reach out to me.


GitHub: REMnux Release

MalChela User Guide: Online, PDF, Web

Shop: T-shirts, hats, stickers, and more

Installing REMnux on a MacBook Pro

I had an older MacBook Pro (15-inch, 2.53GHz, Mid 2009) that had been unused for a while as it was no longer getting updates from Apple. It’s one of the Intel chip ones and last ran Monterey. I pulled it out of the closet and decided to give it a refresh by installing REMnux on it. The process was pretty straightforward, but there were a couple things noted along the way I thought I’d share.

Start off by downloading the Ubuntu 20.04.6 AMD64 Desktop ISO. Yes, 20.04. Later installations aren’t supported by the REMnux installer.

Next you’ll want to burn the image to a flash drive, and make it bootable, using Rufus (Windows) or Balena Etcher (Mac.) This model MacBook has USB-A ports which seems like a relic compared to the current Macs. You’ll need at least an 8GB flash drive for the Ubuntu image. The first free one I could find was 32GB so I used that.

With the bootable USB drive inserted, power-up the MacBook and hold the option key until you see the different hard drives listed.

The flash drive is the one that shows as EFI Boot. Select it and hit return/enter.

Once everything is booted up you’ll get to the Try or Install Ubuntu menu. We’ll choose install.

Specify options as needed for timezone, keyboard, etc. For the username we’ll use remnux and the password malware as that’s the default. After the installation you can set the password for the remnux user as you wish.

At the Installation type we’ll choose Erase disk and install Ubuntu.

Sorry for the wavy resolution. Tough to get good screenshots during bare-metal OS installations.

Once the installation completes, hit Restart Now.

When I first logged in I was getting an error, “Activation of network connection failed” when trying to authenticate to the wireless network. Disabling IPv6 for that network fixed. it.

Now that we’ve got connectivity, we can grab any available Ubuntu updates.

sudo apt-get update && sudo apt-get upgrade

If at any point you’re prompted to do a distribution upgrade (a version of Ubuntu later than 20.04), choose Don’t Upgrade.

Once you’ve done all the OS updates, and rebooted, we can start the REMnux installation. We’ll be following the Install from Scratch instructions at remnux.org

wget https://REMnux.org/remnux-cli
sha256sum remnux-cli 

Verify the hash matches the published hash 88cd35b7807fc66ee8b51ee08d0d2518b2329c471b034ee3201e004c655be8d6

mv remnux-cli remnux
chmod +x remnux
sudo mv remnux /usr/local/bin

The first time I ran the installer it failed as curl wasn’t installed. So take care of that before starting the install.

sudo apt-get install curl

At this point we’re ready to run the installation. The one deviation I’m choosing here is that rather than the standard install, I’m choosing the ‘cloud mode.’

If you’re depoying REMnux in a remote cloud environment and will need to keep the SSH daemon enabled for remotely accessing the system, use the following command instead to avoid disabling the SSH daemon. Remember to harden the system after it installs to avoid unauthorized logins.

remnux.org

In my case I plan to be ssh’ing into the box from within my own network more often than actual hands on keyboard, hence the cloud mode.

sudo remnux install --mode=cloud

At this point grab a coffee, walk the dog, or find something to do while the wall of text streams by.

Note if the install fails the first time don’t be afraid to re-run the install command a 2nd time.

Finally when it’s done, Reboot.

There you go. A shiny, happy, malware analysis machine.