x.comtooldbugs (@ptdbugs) on X
Decepticon is an open-source framework that automates red team operations with 16 specialized AI agents coordinated by an orchestrator, covering recon, vulnerability research and exploitation against an operator-authorized target in an isolated environment. It offers optional attack planning mapped to MITRE ATT&CK, persistent interactive sessions for Metasploit, Sliver and Evil-WinRM, and findings stored in project files and a knowledge graph. It runs via CLI or web dashboard, integrates with Claude Code and Codex through an MCP server, and is self-hosted with Docker Compose.
TL;DR Decepticon: self-hosted multi-agent (16 agents) AI red-team framework driving Metasploit/Sliver/Evil-WinRM, with ATT&CK-mapped planning and MCP integration.
Organisations named here
- BitterSecurity
- Decepticon
Technologies named here
- dbugs
- Metasploit
- Claude Code
- Codex
- Model Context Protocol
- Docker
- MITRE ATT&CK
- Evil-WinRM
- Sliver
Techniques named here
- Automated red team operations with AI agents
- Multi-agent orchestration
Related in Offensive Security
huntress.comwriteupAI-Coded Malware | Analyzing Vibe-Coded AD Enumeration | Huntress
github.comrepoYesWeHack Claude Kit
huntress.comwriteupInside an Oracle Database SQL Injection Attack | Huntress
huntress.comwriteup