skill-vetterSecurity-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
Install via ClawdBot CLI:
clawdbot install spclaudehome/skill-vetterSecurity-first vetting protocol for AI agent skills. Never install a skill without vetting it first.
Questions to answer:
- [ ] Where did this skill come from?
- [ ] Is the author known/reputable?
- [ ] How many downloads/stars does it have?
- [ ] When was it last updated?
- [ ] Are there reviews from other agents?Read ALL files in the skill. Check for these RED FLAGS:
šØ REJECT IMMEDIATELY IF YOU SEE:
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā¢ curl/wget to unknown URLs
ā¢ Sends data to external servers
ā¢ Requests credentials/tokens/API keys
ā¢ Reads ~/.ssh, ~/.aws, ~/.config without clear reason
ā¢ Accesses MEMORY.md, USER.md, SOUL.md, IDENTITY.md
ā¢ Uses base64 decode on anything
ā¢ Uses eval() or exec() with external input
ā¢ Modifies system files outside workspace
ā¢ Installs packages without listing them
ā¢ Network calls to IPs instead of domains
ā¢ Obfuscated code (compressed, encoded, minified)
ā¢ Requests elevated/sudo permissions
ā¢ Accesses browser cookies/sessions
ā¢ Touches credential files
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāEvaluate:
- [ ] What files does it need to read?
- [ ] What files does it need to write?
- [ ] What commands does it run?
- [ ] Does it need network access? To where?
- [ ] Is the scope minimal for its stated purpose?| Risk Level | Examples | Action |
|------------|----------|--------|
| š¢ LOW | Notes, weather, formatting | Basic review, install OK |
| š” MEDIUM | File ops, browser, APIs | Full code review required |
| š“ HIGH | Credentials, trading, system | Human approval required |
| ā EXTREME | Security configs, root access | Do NOT install |
After vetting, produce this report:
SKILL VETTING REPORT
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
Skill: [name]
Source: [ClawdHub / GitHub / other]
Author: [username]
Version: [version]
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
METRICS:
ā¢ Downloads/Stars: [count]
ā¢ Last Updated: [date]
ā¢ Files Reviewed: [count]
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
RED FLAGS: [None / List them]
PERMISSIONS NEEDED:
ā¢ Files: [list or "None"]
ā¢ Network: [list or "None"]
ā¢ Commands: [list or "None"]
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
RISK LEVEL: [š¢ LOW / š” MEDIUM / š“ HIGH / ā EXTREME]
VERDICT: [ā
SAFE TO INSTALL / ā ļø INSTALL WITH CAUTION / ā DO NOT INSTALL]
NOTES: [Any observations]
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāFor GitHub-hosted skills:
# Check repo stats
curl -s "https://api.github.com/repos/OWNER/REPO" | jq '{stars: .stargazers_count, forks: .forks_count, updated: .updated_at}'
# List skill files
curl -s "https://api.github.com/repos/OWNER/REPO/contents/skills/SKILL_NAME" | jq '.[].name'
# Fetch and review SKILL.md
curl -s "https://raw.githubusercontent.com/OWNER/REPO/main/skills/SKILL_NAME/SKILL.md"Paranoia is a feature. šš¦
Generated Mar 1, 2026
Developers vetting third-party skill packages from GitHub before integrating them into their AI agents to prevent malicious code injection. This ensures security when extending agent capabilities with community contributions.
IT security teams evaluating skills from marketplaces like ClawdHub before deployment in corporate AI assistants. This mitigates risks of data breaches or unauthorized system access in regulated environments.
Researchers vetting experimental skills from shared repositories to safely test new functionalities without compromising lab systems or sensitive data. This supports secure collaboration in AI studies.
Consultants vetting skills for client projects to ensure compliance with security standards and avoid liability from installing untrusted code. This builds trust when customizing AI solutions for businesses.
Support teams vetting skills that handle customer data or integrate with CRM systems to prevent privacy violations. This maintains compliance with data protection regulations like GDPR.
Offer a premium vetting service with automated scans and human reviews for AI skills, charging monthly fees per agent or skill package. Revenue comes from enterprises needing compliance and risk management.
Partner with skill marketplaces like ClawdHub to provide vetting as a built-in feature, earning commissions on verified skill sales or listing fees. This monetizes trust in third-party platforms.
Provide custom vetting protocols, security audits, and training workshops for organizations deploying AI agents. Revenue is generated through project-based contracts and certification programs.
š¬ Integration Tip
Integrate vetting into CI/CD pipelines to automatically scan skills before deployment, using the provided curl commands for GitHub checks.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
Perform a comprehensive read-only security audit of Clawdbot's own configuration. This is a knowledge-based skill that teaches Clawdbot to identify hardening opportunities across the system. Use when user asks to "run security check", "audit clawdbot", "check security hardening", or "what vulnerabilities does my Clawdbot have". This skill uses Clawdbot's internal capabilities and file system access to inspect configuration, detect misconfigurations, and recommend remediations. It is designed to be extensible - new checks can be added by updating this skill's knowledge.
Use when reviewing code for security vulnerabilities, implementing authentication flows, auditing OWASP Top 10, configuring CORS/CSP headers, handling secrets, input validation, SQL injection prevention, XSS protection, or any security-related code review.
Security check for ClawHub skills powered by Koi. Query the Clawdex API before installing any skill to verify it's safe.
Scan Clawdbot and MCP skills for malware, spyware, crypto-miners, and malicious code patterns before you install them. Security audit tool that detects data exfiltration, system modification attempts, backdoors, and obfuscation techniques.
Safe command execution for OpenClaw Agents with automatic danger pattern detection, risk assessment, user approval workflow, and audit logging. Use when agen...