The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown and code examples demonstrating architectural patterns. No malicious behavior or technical vulnerabilities were identified.
[PROMPT_INJECTION]: The instructions are strictly focused on architectural validation and refactoring. There are no attempts to override system prompts, bypass safety filters, or extract system instructions.
[DATA_EXFILTRATION]: No network operations (curl, wget, fetch) or access to sensitive credential files (.env, .aws, .ssh) were detected. All file paths mentioned are standard application source code locations.
[REMOTE_CODE_EXECUTION]: No remote script downloads or dynamic code execution patterns (eval, exec) are present. The skill does not automate the installation of external packages.
[COMMAND_EXECUTION]: The skill does not invoke shell commands or perform privilege escalation operations.
[OBFUSCATION]: All content is provided in plain text. There is no use of Base64 encoding, zero-width characters, or homoglyph-based evasion techniques.

clean-architecture