Hack Me — Security skill for Claude Code
Attack your own running app on localhost, prove each vuln is real, patch it, and re-verify.
How to install Hack Me
Installs to ~/.claude/skills/kulchankas-paranoid-hack-me/SKILL.md
mkdir -p ~/.claude/skills/kulchankas-paranoid-hack-me && curl -fsSL https://raw.githubusercontent.com/kulchankas/paranoid/HEAD/commands/hack-me.md -o ~/.claude/skills/kulchankas-paranoid-hack-me/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Hack Me does
description: Attack your own running app on localhost, prove each vuln is real, patch it, and re-verify.
/hack-me
Turn the `paranoid` review into proof. Instead of *telling* the user their code has an IDOR, you demonstrate it against their own app on localhost, then fix it and show the exploit now fails.
Scope — read first, enforce always
This runs **only** against an app the user owns and is running locally. Before touching anything:
- Target must be local.
localhost, `1
Alternatives in Security
- Maestro Odyssey — Long-running iterative cycle — one entry, seven modes (debug improve planex review security defensive ui) 530 ★
- Skill Threat Modeling — Code-First Deep Risk Analysis Skill for Claude Code - 8-Phase Workflow with Security design review, STRIDE Thr 207 ★
- Public Skills Builder — Generate Claude Code bug bounty skills from public HackerOne reports and GitHub writeups — 18 vuln classes, no 155 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Hunt
Start hunting on a target — loads scope, reads disclosed reports, picks best attack surface based on tech stac
Citecheck
Audit every legal citation in a draft: extract deterministically, prove each authority exists, then verify it
API Test Suite
Add unit/integration/security tests to a FixIt API module via questionnaire-driven scoping and agent dispatch
Walkthrough Nt
Role-driven browser walkthrough — identify each user role, drive the running app through their journeys in a r
Cve Env
Agentic CVE → Docker environment builder: given a CVE ID, builds and verifies a Docker environment running the
Sec Triage Agent
Autonomous LLM security triage agent built with Python, Claude Code, Ollama, and Pydantic. Automatically parse
Related Agents
Infra Vuln Management
CVE prioritization and patch sequencing. Mostly mechanical lookups against your inventory. Peer to infra-secur
Webtester
Use this agent to verify that a web app actually works end-to-end in a real browser, driven by Playwright agai
Deal Verifier
Adversarially tries to break proposed contract patches and verifies source-document integrity. Default verdict