devtools

Decepticon: AI‑Powered Red‑Team Agent for Faster Pentests

Name: Decepticon: AI‑Powered Red‑Team Agent for Faster Pentests
Author: PurpleAILAB

Deploy Decepticon to automate offensive security workflows, letting founders and security teams run smart, scalable penetration tests with minimal manual effort.

From the repo · “Autonomous Hacking Agent for Red Team”

6,392 stars+285★ this week1,231 forksPythonGuide quality 9/10 · reviewed Oct 17Updated 10/22/2026100% free · open source

What it does

Decepticon is an autonomous hacking agent that provides red team support for founders, enabling them to test their system's security and identify vulnerabilities.

When to use it

•You need to test your system's security without manual intervention
•You want to identify potential vulnerabilities in your system
•You require a red team to simulate real-world attacks on your system

Ready-to-paste prompt

python decepticon.py -t target_ip -p target_port -m exploitation_module

Heads up: Before running Decepticon, ensure you have Python 3.8 or higher installed, as the tool is not compatible with lower versions, and also make sure to configure the exploit modules according to your needs

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/decepticon && curl -fsSL https://workflowstacks.com/api/skills/decepticon/claude-skill -o ~/.claude/skills/decepticon/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Decepticon: AI‑Powered Red‑Team Agent for Faster Pentests works

Codeflow

Free to inspect

Decepticon: AI‑Powered Red‑Team Agent for Faster Pentests is a very large Python project (~121k lines across 654 code files, plus 319 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size

Very large codebase

~121k lines · 654 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Python · Docker

Needs API keys (.env)

Python 49%Cypher 40%TypeScript 6%Go 4%JavaScript 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
package.json
Dependencies and the commands it exposes
3
.env.example
The API keys and settings you must provide

What's in each folder

packages/Sub-packages / plugins1064 files

integrations/Sub-packages / plugins3 files

docs/Documentation91 files

benchmark/Evaluations & benchmarks492 files

clients/SDKs / client libraries276 files

telemetry-gateway/Folder18 files

config/Configuration14 files

containers/Folder12 files

READMEHas testsDocumentedCI checksDocker readyApache-2.0 licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/decepticon && curl -fsSL https://workflowstacks.com/api/skills/decepticon/claude-skill -o ~/.claude/skills/decepticon/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

PurpleAILAB

Language

Python