The Agent Skills Directory

[SAFE]: The skill is a security-focused tool designed to improve project hygiene and environment consistency. It implements logic to detect sensitive data exposure (e.g., scanning for high-entropy strings like API keys in .env files) and advises the user on remediation.
[COMMAND_EXECUTION]: The skill utilizes Bash, Grep, and Glob to scan the local file system for configuration signals and potential risks. These tools are used appropriately within the scope of the skill's primary purpose—detection and reporting—without evidence of malicious command injection or privilege escalation.
[EXTERNAL_DOWNLOADS]: The skill provides a GitHub Actions template (templates/ci-matrix-github-actions.yml) that references well-known and trusted external actions (e.g., actions/checkout@v4, actions/setup-node@v4, pnpm/action-setup@v4). These references are standard for CI/CD workflows and do not contribute to a negative verdict.
[CREDENTIALS_SAFE]: The skill explicitly includes logic to detect hardcoded secrets (=sk_, =ghp_, =AKIA) and flags them as critical risks. It promotes the use of environment variable validators and secret managers rather than hardcoding credentials.
[NO_CODE]: The skill primarily consists of instructional markdown and configuration templates. The provided Node.js and Python scripts are boilerplate validators intended for the user's project, utilizing standard libraries like zod and pydantic-settings to enforce type safety in environment configurations.

env-parity-baseline