by weirdmachine64 · Agent Tool · ★ 825
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/weirdmachine64/GhidraGPT.git
Taken from the project's README on GitHub. Check the security audit before running it.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 825 |
| Forks | 147 |
| Language | Java |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 63/100 |
| Open Issues | 1 |
| Last Updated | 2026-07-22 |
| Created | 2025-09-12 |
| Platforms | java |
| Est. Tokens | ~17k |
GhidraGPT Author: Mohamed Benchikh GhidraGPT is a Ghidra extension that brings large language models into the decompiler workflow. You right-click a function; the plugin sends that function's decompiled C to an LLM provider of your choice and streams the response back into a dedicated console.
These tools work well together with GhidraGPT for enhanced workflows:
Looking for a GhidraGPT alternative? If you're comparing GhidraGPT with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
An native MCP server extension for Ghidra
An MCP extension for Ghidra
Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.
Plugin for JADX to integrate MCP server
Conquer Any Code in VSCode: One-Click Comments, Conversions, UI-to-Code, and AI Batch Processing of Files! 在 V
Reconstruct and validate C/C++ code from compiled programs with AI.
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: