The Agent Skills Directory

[SAFE]: The skill serves as an educational resource and does not perform any autonomous actions or include risky command executions.
[PROMPT_INJECTION]: While the skill defines a specific behavior for its initial response, it does not attempt to override system safety protocols, bypass filters, or use adversarial techniques like 'Ignore previous instructions'.
[DATA_EXFILTRATION]: No network access commands (e.g., curl, wget) or sensitive file path references (e.g., .env, .ssh) are present in the documentation.
[REMOTE_CODE_EXECUTION]: The skill does not download, install, or execute any third-party packages or scripts. All code examples are for educational purposes and promote safe programming practices.
[OBFUSCATION]: The text and code snippets are entirely transparent. No Base64 encoding, zero-width characters, or homoglyph attacks were detected.
[DYNAMIC_CONTEXT_INJECTION]: The skill does not use the shell execution syntax ('!command') in its documentation.

write-swift