The Agent Skills Directory

[SAFE]: The skill's operation is confined to local file system analysis using tools like Read, Grep, and Glob. It lacks network access and file writing capabilities, ensuring it cannot exfiltrate data or modify the environment.- [SAFE]: External references in the documentation and reference files are limited to well-known, trusted technology documentation sites such as MDN Web Docs and Refactoring Guru.- [SAFE]: The skill instructions and YAML configuration files (signatures, checklists, and references) contain no evidence of prompt injection, obfuscation, or credential harvesting. The regex patterns used for detection are standard for code analysis purposes.- [SAFE]: While the skill processes untrusted codebase data (Category 8 surface), it has no high-risk capabilities (like network communication or shell execution) that would enable an indirect prompt injection attack to cause significant harm.

design-patterns