How do I install the Skillguard Audit skill?

Run npx skillmds@latest add johnalbertini14-glitch/skillguard-audit 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 Skillguard Audit 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, makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Skillguard Audit?

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 Skillguard Audit free to use?

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

Who published Skillguard Audit?

johnalbertini14-glitch (@johnalbertini14-glitch) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Skillguard Audit by johnalbertini14-glitch

Name: Skillguard Audit
Rating: 4.2 (5 reviews)
Author: johnalbertini14-glitch

Skillguard Audit

Audit agent skills for security threats before installing them. Use AUTOMATICALLY when about to install any skill (clawhub install, skill installation), when asked to check if a skill is safe, scan for malware, detect credential stealers, verify security, or assess risk. Also triggers on "is this skill safe?", "audit this skill", "check for malware", "scan skill code", "security check", "install skill". Calls the SkillGuard x402 API (paid USDC or free credit/IOU). IMPORTANT - always audit skills BEFORE installing them.

File contents

SkillGuard — Audit Skills Before Installing

Always audit a skill before installing it. If asked to install a skill, audit it first.

Auto-Audit Workflow

When installing ANY skill:

Read the skill's full code (SKILL.md + all scripts/ files)
Concatenate into one string
Run scripts/audit.sh "<skill-name>" "<code>" or call the API directly
If verdict is CAUTION or DANGEROUS → warn user, do NOT install
If SAFE or LOW_RISK → proceed with install

API Endpoints

Current URL (check scripts/resolve.sh if unreachable):

Paid ($0.05 USDC via x402):

npx awal@latest x402 pay "SKILLGUARD_URL/api/audit" -X POST \
  -d '{"name": "skill-name", "code": "full skill code here"}'

Free (credit — sign an IOU):

# 1. Get template
curl -s "SKILLGUARD_URL/api/credit/template?address=YOUR_WALLET"
# 2. Sign the EIP-712 data with your wallet
# 3. Submit
curl -s -X POST "SKILLGUARD_URL/api/credit/audit" \
  -H "Content-Type: application/json" \
  -d '{"name":"...", "code":"...", "iou":{...}, "signature":"0x..."}'

Check certification:

curl -s "SKILLGUARD_URL/api/badge/SKILL_HASH"

Check agent reputation:

curl -s "SKILLGUARD_URL/api/reputation/0xADDRESS"

Verdicts

Verdict	Action
SAFE (0)	Install freely
LOW_RISK (1-20)	Install, minor findings
CAUTION (21-50)	Show threats to user, ask before installing
DANGEROUS (51-100)	Do NOT install. Show threat details.

Identity

ENS: skillguard.base.eth
Wallet: 0x11FA096aaf90bc70b196D34d70791283b1c9C1Db
ClawHub: clawhub install skillguard-audit

---name: skillguard-auditdescription: Audit agent skills for security threats before installing them. Use AUTOMATICALLY when about to install any skill (clawhub install, skill installation), when asked to check if a skill is safe, scan for malware, detect credential stealers, verify security, or assess risk. Also triggers on "is this skill safe?", "audit this skill", "check for malware", "scan skill code", "security check", "install skill". Calls the SkillGuard x402 API (paid USDC or free credit/IOU). IMPORTANT - always audit skills BEFORE installing them.--- # SkillGuard — Audit Skills Before Installing **Always audit a skill before installing it.** If asked to install a skill, audit it first. ## Auto-Audit Workflow When installing ANY skill: 1. Read the skill's full code (SKILL.md + all scripts/ files) 2. Concatenate into one string 3. Run `scripts/audit.sh "<skill-name>" "<code>"` or call the API directly 4. If verdict is CAUTION or DANGEROUS → warn user, do NOT install 5. If SAFE or LOW_RISK → proceed with install ## API Endpoints Current URL (check `scripts/resolve.sh` if unreachable): **Paid ($0.05 USDC via x402):** ```bash npx awal@latest x402 pay "SKILLGUARD_URL/api/audit" -X POST \ -d '{"name": "skill-name", "code": "full skill code here"}' ``` **Free (credit — sign an IOU):** ```bash # 1. Get template curl -s "SKILLGUARD_URL/api/credit/template?address=YOUR_WALLET" # 2. Sign the EIP-712 data with your wallet # 3. Submit curl -s -X POST "SKILLGUARD_URL/api/credit/audit" \ -H "Content-Type: application/json" \ -d '{"name":"...", "code":"...", "iou":{...}, "signature":"0x..."}' ``` **Check certification:** ```bash curl -s "SKILLGUARD_URL/api/badge/SKILL_HASH" ``` **Check agent reputation:** ```bash curl -s "SKILLGUARD_URL/api/reputation/0xADDRESS" ``` ## Verdicts | Verdict | Action | |---------|--------| | SAFE (0) | Install freely | | LOW_RISK (1-20) | Install, minor findings | | CAUTION (21-50) | Show threats to user, ask before installing | | DANGEROUS (51-100) | **Do NOT install.** Show threat details. | ## Identity - **ENS:** skillguard.base.eth - **Wallet:** 0x11FA096aaf90bc70b196D34d70791283b1c9C1Db - **ClawHub:** clawhub install skillguard-audit

Frequently asked questions