By HacktronAI
Validate and triage Hacktron security findings against source code and a live deployment, distinguishing true from false positives, adjusting severity, and committing fixes or updating finding states via the Hacktron API.
Community-maintained skills for offensive and defensive security capabilities. Built for security researchers, engineers, and bug hunters.
Skills extend AI agents with specialized security capabilities. When enabled, skills provide domain-specific instructions, scripts, and references that help agents perform complex security tasks.
This repository follows the Agent Skills specification.
This repo is also a Claude Code plugin marketplace. Each skill is installable as a plugin.
# Register the marketplace
/plugin marketplace add HacktronAI/skills
# Browse and install from the menu
/plugin menu
# Or install a specific skill directly
/plugin install finding-triage@hacktron
Install from a local clone instead:
git clone https://github.com/HacktronAI/skills.git
# From the parent directory of the clone
/plugin marketplace add ./skills
/plugin install finding-triage@hacktron
# Pull the skills registry
hacktron skills pull
# List available skills
hacktron skills list
# Enable a skill
hacktron skills enable patch-diff-analyzer
# Disable a skill
hacktron skills disable patch-diff-analyzer
Skills are automatically discovered and can be enabled/disabled from the extension settings.
| Skill | Description | Sources |
|---|---|---|
| finding-triage | Interactively triage Hacktron findings against source (and optionally a live deployment), then fix + commit confirmed issues or set their state in Hacktron | - |
| patch-diff-analyzer | Reverse-engineer compiled binaries (JARs, DLLs) to analyze security patches | - |
Skills from other repositories that follow the Agent Skills specification can be used with Hacktron:
To use skills from other repositories, manually copy them into ~/.hacktron/skills/:
# Copy individual skills from other repos
cp -r /path/to/other-repo/skill-name ~/.hacktron/skills/
Security Warning: Skills can execute arbitrary commands on your machine. Always review the
SKILL.mdand any scripts before adding skills from third-party sources. Only the official HacktronAI/skills repository is reviewed and validated for security.
Note: The
hacktron skills pullcommand only pulls from the official HacktronAI/skills repository. Third-party skills must be manually copied to ensure users consciously review what they're installing.
Skills follow the Agent Skills specification. Each skill is a directory containing:
skill-name/
├── SKILL.md # Required - YAML frontmatter + instructions
├── scripts/ # Optional - executable scripts
├── references/ # Optional - additional documentation
└── assets/ # Optional - templates, data files
---
name: skill-name
description: What the skill does and when to use it.
license: MIT
compatibility: Required tools or environment
metadata:
author: your-name
version: "1.0.0"
---
# Skill Name
Instructions for the agent...
hacktron skills enable your-skillAll skills are reviewed for security before being merged.
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub hacktronai/skills --plugin finding-triageReverse-engineer compiled binaries (JARs, DLLs) to decompile, diff, and analyze security patches.
Bulk triage workflow for all assigned HackenProof programs
Security research toolkit for discovering and remediating vulnerabilities
Systematic false positive verification for security bug analysis with mandatory gate reviews
Meta-tool for generating security audit Skills from GHSA and HackerOne data
Specialized security review subagent
71-skill bug-hunting & external red-team bundle for Claude Code — 48 hunt-* web/vuln-class + framework skills, enterprise platform attack chains (M365/Entra, Okta, SharePoint, vCenter, SSL-VPN, APK), recon/OSINT, reporting & validation gates, and Burp MCP integration. Skills auto-load by topic; 15 slash commands included.