ArchestackBest of Open-Source AI: List on GitHub ↗ (opens in a new tab)

#1919th of 23 in Security

dsh-infinite-gen-5

Reverse-engineering plugin for DeepSeek Harness using Ghidra, x64dbg and Unicorn

Documentation ↗ (opens in a new tab)Repository on GitHub ↗ (opens in a new tab)
Stars
2.7k
License
custom license
Last commit
Oct 2026
Last release
Oct 2026
Language
JavaScript

Missed the latest GitHub check; these facts may be older.

Overview

IG5 is a plugin for DeepSeek Harness (DSH) that exposes 43 reverse-engineering tools and 8 workflow skills to an agent. It combines Ghidra static analysis, x64dbg native debugging and Unicorn single-function emulation with HTTP/HTTPS capture, XOR/AES candidate search and protocol framing. Thirteen modify or execute tools require host approval before running. Ships as a self-contained Windows x64 package.

Who it is for: Reverse engineers and security researchers using DeepSeek Harness on Windows

Strengths

  • Bundles Ghidra, JDK, Python and x64dbg in the Windows package; no commercial IDA needed
  • 13 mutating or executing tools gated by host approval, with undo and audit log
  • Per-function dossier combines pseudocode, CFG, call graph and stack frame from one revision
  • Default Core 8 toolset keeps the tool surface small; Full 43 is opt-in

Weaknesses

  • Requires an existing DeepSeek Harness install, pinned to >=0.2.0-rc.1 <0.3.0-0
  • Full support only on Windows x64; macOS is Ghidra static only and experimental
  • CC BY-NC-SA 4.0 license forbids commercial use
  • README is heavy on self-promotion; star and fork counts there differ from detected 2,745

What it needs

  • Needs DeepSeek Harness (@deepseek-ai/dsh >=0.2.0-rc.1 <0.3.0-0), Ghidra, x64dbg, Unicorn, PowerShell

Also in Security

See all 23
Also in Security
RankProjectScore
1shannonAutonomous pentester that exploits web apps and APIs using source analysis51.8k stars+3,117 (+6.4%) in 30 daysAGPL-3.092 out of 100
2ifixaiPython CLI that audits AI agents for policy, access and reliability failures45k starsApache-2.087 out of 100
3StrixAutonomous AI pentesting agents that validate vulnerabilities with working exploits75.1k starsApache-2.084 out of 100
#4ai-infra-guardRed-teaming platform for AI infra CVEs, MCP servers, agent skills and jailbreaks7.5k stars+669 (+9.8%) in 30 daysApache-2.079 out of 100
#5pentagiAutonomous multi-agent penetration testing system with sandboxed security tools34k stars+6,715 (+25%) in 30 daysMIT78 out of 100