How do I install the Hadriansecurity Openhack skill?

Run npx skillmds add yanacuti1121/hadriansecurity-openhack in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Hadriansecurity Openhack safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Hadriansecurity Openhack?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Hadriansecurity Openhack free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Hadriansecurity Openhack?

yanacuti1121 (@yanacuti1121) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Hadriansecurity Openhack by yanacuti1121

Name: Hadriansecurity Openhack
Rating: 4.2 (5 reviews)
Author: yanacuti1121

Hadriansecurity Openhack

Whitebox security review agent — checkpointed pentest workflow: recon → scenario routing → expert agents (12 OWASP families) → triage → findings. Runs inside Claude Code, Codex, or Cursor.

yanacuti1121 b8d9c6c 1.4 KB Updated Sep 9, 2026 2 repo stars

File contents

Whitebox pentest workflow from Hadrian Security. Checkpointed, file-based state.

Quick start

# Install
pip install openhack

# Run against a repo
openhack init-run <target> <git-url>

Or simply ask the agent:

Initiate a whitebox pentest on https://github.com/example/app.git

Flow (10 phases, human approves each)

openhack init-run — clone target, init run state
Select experts (12 OWASP families or subset)
openhack run-recon — surface discovery, writes routing-units.jsonl
openhack create-scenarios — router agent generates scenario backlog
Run scenario backlog — each scenario gets its own expert agent + evidence
openhack record-scenario-result — records finding candidates
openhack render-finding-triage-prompt — triage prompt per candidate
openhack record-finding-triage — accepted/downgraded → final findings
openhack validate-run — integrity check

Key principle

Recon is scouting only. Do NOT begin vulnerability analysis from recon alone. Each phase requires human approval before proceeding.

Source

https://github.com/hadriansecurity/openhack

Frequently asked questions