Skill Security Vendor Pack
Audit AI agent skills for security risks, packaging errors, and marketplace readiness with professional reports.
Free
Works with the AI Agents you already use
skill-security-vendor-pack
Example session with this skill installed
Audit my local SEO-audit-skill folder and save the results to output.json and report.md.
- Read your context and instructions
- Compiled the -security-vendor-
Security Review: [PASS/WARNING]
- Risk Level: Medium
- Issues:
- Found 'subprocess.run' call in skill.py (Suspicious Pattern)
- Missing 'tags' in skill.yaml (Packaging Issue)
- JSON artifacts saved to output.json.
- Full Markdown report generated for client delivery.
Connects securely to your tools. The creator never sees your data.
About this skill
Ensure Professional Credibility for Your AI Skills
The Skill Security Vendor Pack is a specialized auditing tool designed for developers and agencies building for AI marketplaces. It automates the pre-flight inspection of skill packages, ensuring they meet the high standards required for commercial distribution and client delivery.
What it does
This skill performs a deep-dive scan of a skill folder to identify security risks, packaging defects, and marketplace-readiness gaps. It replaces manual checklists with an automated, script-based review process that generates both developer-friendly JSON data and client-ready Markdown reports.
- Permission Auditing: Scans for high-risk or over-scoped permissions that might block marketplace approval.
- Pattern Matching: Flags suspicious code patterns or shell execution risks that require manual verification.
- Packaging Validation: Checks for missing configuration files, metadata inconsistencies, and directory structure errors.
- Portable Analysis: Built with zero-dependency Python for easy inclusion in CI/CD pipelines or local development workflows.
Why use this skill?
While basic prompting might catch high-level errors, this skill follows a strict Output Contract, ensuring every report is structured for professional use. It provides evidence-backed flags rather than generic warnings, allowing you to fix issues before they become "denied" statuses on a marketplace or security concerns for a client. It effectively turns your audit process into a repeatable, professional service.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Security.
- Scans are signature-based and may miss highly obfuscated code.
- Does not perform dynamic sandbox execution or network traffic analysis.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
This skill has been used 36 times.
Trust & safety
Security scan
Security scan passed 7 months ago
- Free with an Agensi account
- Software
Python