The Agent Skills Directory

[SAFE]: The skill consists entirely of architectural guidance and static code examples. No malicious patterns or security risks were identified during the analysis of the documentation or the provided code snippets.
[PROMPT_INJECTION]: No evidence of prompt injection attempts or instructions to bypass safety filters. The instructions focus exclusively on software engineering principles.
[CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or sensitive file paths were detected. Code examples use standard placeholders or constructor injection for configuration.
[EXTERNAL_DOWNLOADS]: The skill does not perform any external network requests or download third-party resources at runtime.
[REMOTE_CODE_EXECUTION]: There are no patterns involving the execution of remote scripts or unverified code. All examples are localized and self-contained.
[COMMAND_EXECUTION]: No shell commands, privilege escalation attempts (sudo), or persistence mechanisms were found in any of the files.
[OBFUSCATION]: All content is written in clear, plain text. No Base64, hex encoding, zero-width characters, or hidden URLs were identified.
[INDIRECT_PROMPT_INJECTION]: The skill does not define ingestion points for untrusted data or automate execution based on external content, posing no risk for indirect injection.

clean-architecture