The Agent Skills Directory

[SAFE]: The skill serves as a comprehensive security reference and checklist for the AI agent to follow when reviewing or generating code. It covers critical security topics like SQL injection prevention, XSS mitigation, and cloud infrastructure hardening through clear documentation and best-practice examples.
[CREDENTIALS_SAFE]: All hardcoded strings in the documentation are clearly identified as negative examples of insecure practices (e.g., 'sk-proj-xxxxx', 'password123'). The skill correctly instructs the agent to use environment variables and dedicated cloud secret managers.
[EXTERNAL_DOWNLOADS_SAFE]: The skill references well-known security tools and official GitHub Actions (e.g., TruffleHog for secret scanning, official AWS actions). These references are for documentation and provide secure defaults for CI/CD pipelines.
[COMMAND_EXECUTION_SAFE]: Example shell commands provided (e.g., npm audit, aws iam enable-mfa-device) are standard administrative and security auditing tools used in routine development and infrastructure maintenance.

security-review