Works with the AI tools you already use
Skill Install Safety Gate
by Roy Yuen
Automated security and compatibility firewall for installing AI agent skills and Codex/OpenClaw packages.
Free
See it in action
You say
Run a safety check on the web-scraper.zip file and install it to ~/.codex/skills if it passes all security and compatibility gates.
Your agent does
GATE DECISION: allow SUMMARY: Validated 'web-scraper' v1.2.0. COMPATIBILITY: All bins (python3) found. SECURITY: 0 blockers, 2 review items (network URLs detected). INSTALL: Successfully copied to ~/.codex/skills/web-scraper. Receipt generated: install-receipt.json
About this skill
Protect Your AI Agent Environment
Deploying third-party skills and toolsets into your agent's runtime shouldn't be a leap of faith. The Skill Install Safety Gate provides a rigorous, automated inspection layer designed specifically for Codex and OpenClaw-style skill architectures. It acts as a static analysis firewall, ensuring that new capabilities meet your security and compatibility standards before they ever touch your file system.
What it does
- Structural Validation: Verifies package shape, ZIP integrity, and mandatory SKILL.md metadata.
- Compatibility Mapping: Automatically checks for required binaries (anyBins), environment variables, and config dependencies against your local host.
- Heuristic Security Scanning: Detects suspicious patterns such as ZIP path traversals, obfuscated payloads, prompt-injection risk, and dangerous dynamic code execution patterns.
- Conflict Prevention: Prevents accidental overwrites by checking for existing skill slugs in the target directory.
Why developer-agents need this
Unlike simple prompting, this skill provides a programmatic "Pass/Fail" mechanism. It generates structured JSON and CSV reports, allowing your agent or CI/CD pipeline to make informed, data-driven decisions about software installation. It never executes untrusted code, ensuring the audit process itself is perfectly safe.
Output & Integration
The skill produces a detailed install-safety-report.md for human review and a machine-readable output.json. If the --install-on-pass flag is used, it will only commit the files to your target directory if the gate decision is a clean "allow" with zero blockers or review items.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
11 installs
Downloaded by developers to date
Free forever
No account required to browse
Trust & safety
Security scanned
Verified clean 2 months ago
- Free forever, no account required
Creator
Frequently Asked Questions
Popular in Security & Compliance
Bounty Security Pattern Master Library — 399 Vulnerability Patterns
A premium library of 399 vulnerability patterns and DeFi attack vectors for AI-driven bug hunting and security audits.
🔒 PII & Data-Leak Scanner
Scan your schemas, seed data, config, and logs for personal data before it leaks. Detects PII-indicating column and key names (email, ssn, phone, address) across SQL, CSV, and JSON, plus PII in the data itself: email addresses, SSN-like numbers, credit-card-like numbers, phone numbers, and PII written into log files. Each finding is flagged with its location and a GDPR-style review note. Heuristic by design: it surfaces what to review, not a compliance guarantee.
skill-security-vendor-pack
Audit AI agent skills for security risks, packaging errors, and marketplace readiness with professional reports.
dependency-auditor
Audit dependencies for security, licenses, and health while generating a phased, low-risk upgrade and migration plan.