Skip to main content
affpapa.org
RU EN
skill CX Codex

openclaw-security-watchdog — Claude Code skill: setup and review

Runs automated security inspections across 14 areas and produces readable status reports. Useful for catching exposed secrets, misconfigured permissions, and backdoor tasks.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add reason-machines/security-skills --skill openclaw-security-watchdog -a claude-code
Open on GitHub

What openclaw-security-watchdog does

The scanner evaluates system integrity across multiple vectors. It examines Node.js runtime status, sensitive directory permissions, scheduled cron tasks, and network entry points. Code scanning detects hardcoded API tokens or credentials directly inside repository files.

Two operational modes are available. Local-only mode runs entirely offline, keeping all telemetry strictly on your machine. The full profile queries threat databases, which requires setting up the OPENCLAW_THREAT_INTEL_API_KEY environment variable.

Execution requires Node.js v18 or later. Without this runtime version, the inspection script will fail. Findings are written to ~/.openclaw/security-reports/ with categorized risk ratings.

What it helps with

  • detect hardcoded secrets and tokens in repository source files
  • audit critical file permissions and privilege escalation risks
  • inspect cron jobs and scheduled tasks for persistence backdoors
  • verify component supply chain integrity and package checksums

Example prompts for the agent

  • Run a security audit on the current system
  • Check network exposure and anomalous active processes
  • Execute a local-only security inspection

How to install openclaw-security-watchdog

1Skills CLI (Vercel)

npx skills add reason-machines/security-skills --skill openclaw-security-watchdog -a claude-code

2Manually: put the files in place

~/.claude/skills/openclaw-security-watchdog/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/openclaw-security-watchdog/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about openclaw-security-watchdog

How to install openclaw-security-watchdog in Claude Code?

Run npx skills add reason-machines/security-skills --skill openclaw-security-watchdog -a claude-code. The skill definition file is placed at ~/.claude/skills/openclaw-security-watchdog/SKILL.md.

What is the difference between local and full scanning modes?

Local mode produces zero outbound network traffic and never queries external services. Full mode checks threat intelligence endpoints and sends anonymized metadata for risk scoring.

What are the prerequisites to run this skill?

You need Node.js v18 or higher installed on your system. Configuration settings and excluded directories can be adjusted in ~/.openclaw/security-watchdog.json.

Similar skills

All skills for Security →
git-guardrails-claude-code Matt Pocock This skill adds a Claude Code hook that stops risky Git commands before they run. Use it when an agent must not push or discard working-tree changes. 499,069installs ponytail-review DietrichGebert ponytail-review reviews a change beyond the diff, checking connected code, bugs, risks, load, tests, speed, and unnecessary code. Use it for PRs and commits. CX Codex +1 57,000installs ponytail-audit DietrichGebert It audits a repository and ranks bugs, risks, and redundant code in a one-shot report. Use it when you need a review without code changes. CX Codex +1 45,400installs security-audit cloudflare Reviews codebases and APIs for vulnerabilities using safe sandboxing. Fits pre-release security reviews, pen-test triage, and architecture checks. CX Codex +1 54,800installs security-and-hardening addyosmani Guides threat modeling and security checks for code that handles user input, authentication, sessions, or external services. Use it when building a feature that accepts untrusted data or reviewing code before release. CX Codex +1 70,200installs supabase official supabase Guides the agent through database configuration and strict RLS policies in Supabase. CX Codex GP ChatGPT 8installs

From the same set69

autopentestx-automated-pentesting This skill automates reconnaissance, vulnerability checks, and security reports. Use it to assess hosts, target lists, and web applications. CX Codex +1 1,100installs vibe-security-skill Audits code written with an AI assistant for the usual holes: exposed keys, broken RLS policies, weak auth. CX Codex +1 1,100installs security-threat-awareness Flags repositories that disguise malicious downloads as legitimate security tools. Use it before installing software from GitHub. CX Codex +1 1,000installs malware-analysis-dragonflyTomb-avast A skill for pulling apart repositories that pose as antivirus installers. It helps you tell a fake distribution from the real thing. CX Codex +1 1,000installs avast-security-analysis This skill examines Avast components, runtime defenses, and behavioral detection. Use it when researching antivirus internals on Windows. CX Codex +1 1,000installs avast-premium-security-awareness A skill that flags repositories posing as antivirus software while actually pushing malware. CX Codex +1 1,000installs avast-premium-security-malware-detection This skill inspects suspicious repositories posing as antivirus installers and points out where malware distribution starts. CX Codex +1 989installs mcp-security-hub This skill spins up 38 Dockerized MCP servers for offensive security tooling and wires them into an AI assistant. CX Codex +1 987installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor