Skip to content
TakoAPI
Back to skills

macarena-test

by misirov

Coding Agents & IDEs
1.1kDownloads reported by clawskills.sh
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Security audit and threat model for OpenClaw gateway hosts.

Description

What This Skill Does

Clawstrike audits an OpenClaw gateway deployment for misconfigurations and real-world attack paths. It runs a verified collection script, evaluates configuration, network exposure, filesystem hygiene, and installed skills/plugins, then produces an OK/VULNERABLE report with severity ratings, evidence excerpts, and fix instructions.

Produces a structured, evidence-backed report with automatic secret redaction instead of requiring manual ad-hoc checks across config files, network state, and plugin directories.

When to Use It

  • Checking whether a self-hosted OpenClaw gateway is reachable without authentication
  • Auditing installed skills and plugins for supply chain risks before a team deployment
  • Verifying firewall and port exposure on an OpenClaw host
  • Reviewing filesystem permissions and SUID/SGID binaries on the gateway machine
  • Generating a shareable security report before granting colleagues access to an OpenClaw instance

Example Workflow

INPUT

User asks: audit my OpenClaw deployment and tell me if anything is vulnerable

AGENT
  1. 1

    Run scripts/collect_verified.sh in the current working directory to gather system evidence

  2. 2

    Read verified-bundle.json to obtain timestamp, OS, OpenClaw version, config path, and runtime context

  3. 3

    Evaluate every required check from references/required-checks.md against evidence in the bundle

  4. 4

    Build a concise threat model aligned with the findings using references/threat-model.md

  5. 5

    Emit a findings table with severity, evidence excerpts, and fix instructions for each issue

OUTPUT

A structured OK/VULNERABLE report listing each check result, severity level, redacted evidence, and remediation steps

Installation

clawhub install misirov/macarena-test

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links