How do I install the Openclaw Pc Security skill?

Run npx skillmds@latest add dvcrn/openclaw-pc-security 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 Openclaw Pc Security safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Openclaw Pc Security?

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 Openclaw Pc Security free to use?

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

Who published Openclaw Pc Security?

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

Openclaw Pc Security by dvcrn — Agent Skill

Name: Openclaw Pc Security
Rating: 4.5 (4 reviews)
Author: dvcrn

Openclaw Pc Security

OpenClaw personal-PC security self-check (Windows posture + local audit + optional target probing). Use this skill whenever the user needs to check Windows security posture, detect outdated OpenClaw/npm versions, or investigate security risks like token leaks and exposed ports.

dvcrn Updated Sep 8, 2026 32 repo stars

File contents

OpenClaw PC Security (Windows)

Description

Security self-check and risk alerting for personal computers running OpenClaw, focusing on:

Windows posture (version, last security update date, support status, patch lag)
OpenClaw/npm outdated warnings
Optional port probing and weak-credential/exposure checks for local/LAN OpenClaw targets (authorized use only)

Currently the Windows posture path is the primary completed scope; other OS and more checks can be added later.

When to use

Use this skill when you need to:

Check whether Windows is out of support or significantly behind patch cadence
Detect outdated OpenClaw/npm versions that may cause security concerns
Investigate token/config leaks, exposed ports, and weak-password brute-force risks

Input

Local Windows information (version/build, last hotfix date)
Optional target host/IP and ports for OpenClaw probing

Output

Severity-based findings (Info/Medium/High/Critical)
HTML/JSON report under openclaw-pc-security/output/
- openclaw-pc-security/output/scan_report.html
- openclaw-pc-security/output/scan_report.json

Steps

1) Local audit

python scripts/main.py --audit --npm-view-latest-openclaw --out-dir openclaw-pc-security/output

2) Scan a target (authorized environments only)

python scripts/main.py <target-ip> --ports 18789,18790,18792 --out-dir openclaw-pc-security/output

Notes

Critical: The active probing functionality (including port scanning, weak credential testing, and sensitive path exposure checks) is intrusive by design and must ONLY be used in authorized environments where you have explicit permission to test the target systems.
DO NOT use the scanning functionality against any system you do not own or have explicit authorization to test.
DO NOT upload tokens, credentials, or reports (output/) to public repositories.
Reports are written under openclaw-pc-security/output/ when using the provided scripts.
If Windows 10 is detected: consider upgrading to Windows 11; if not eligible, enroll in Windows 10 ESU to continue receiving updates until 2026-10.
If OpenClaw is outdated: after upgrading, some or all functions may be unavailable; assess carefully.
After the HTML report is generated, print the report path in the chat for the user's reference. Do NOT upload or send the report file unless the user explicitly requests it and provides a secure destination. Reports may contain sensitive information, so always handle them with caution.

---name: openclaw-pc-securitydescription: OpenClaw personal-PC security self-check (Windows posture + local audit + optional target probing). Use this skill whenever the user needs to check Windows security posture, detect outdated OpenClaw/npm versions, or investigate security risks like token leaks and exposed ports.---# OpenClaw PC Security (Windows)## DescriptionSecurity self-check and risk alerting for personal computers running OpenClaw, focusing on:- Windows posture (version, last security update date, support status, patch lag)- OpenClaw/npm outdated warnings- Optional port probing and weak-credential/exposure checks for local/LAN OpenClaw targets (authorized use only)Currently the Windows posture path is the primary completed scope; other OS and more checks can be added later.## When to useUse this skill when you need to:- Check whether Windows is out of support or significantly behind patch cadence- Detect outdated OpenClaw/npm versions that may cause security concerns- Investigate token/config leaks, exposed ports, and weak-password brute-force risks## Input- Local Windows information (version/build, last hotfix date)- Optional target host/IP and ports for OpenClaw probing## Output- Severity-based findings (Info/Medium/High/Critical)- HTML/JSON report under `openclaw-pc-security/output/` - `openclaw-pc-security/output/scan_report.html` - `openclaw-pc-security/output/scan_report.json`## Steps### 1) Local audit```bashpython scripts/main.py --audit --npm-view-latest-openclaw --out-dir openclaw-pc-security/output```### 2) Scan a target (authorized environments only)```bashpython scripts/main.py <target-ip> --ports 18789,18790,18792 --out-dir openclaw-pc-security/output```## Notes- **Critical**: The active probing functionality (including port scanning, weak credential testing, and sensitive path exposure checks) is intrusive by design and must ONLY be used in authorized environments where you have explicit permission to test the target systems.- **DO NOT** use the scanning functionality against any system you do not own or have explicit authorization to test.- **DO NOT** upload tokens, credentials, or reports (output/) to public repositories.- Reports are written under `openclaw-pc-security/output/` when using the provided scripts.- If Windows 10 is detected: consider upgrading to Windows 11; if not eligible, enroll in Windows 10 ESU to continue receiving updates until 2026-10.- If OpenClaw is outdated: after upgrading, some or all functions may be unavailable; assess carefully.- After the HTML report is generated, print the report path in the chat for the user's reference. Do NOT upload or send the report file unless the user explicitly requests it and provides a secure destination. Reports may contain sensitive information, so always handle them with caution.

Frequently asked questions