The Agent Skills Directory

[SAFE]: The skill is purely instructional, focusing on architectural methodology and decision-making processes.
[PROMPT_INJECTION]: No evidence of instructions designed to bypass agent safety filters or override system prompts was found.
[DATA_EXFILTRATION]: No hardcoded credentials, sensitive file path access, or unauthorized network requests are present.
[REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts or untrusted packages.
[COMMAND_EXECUTION]: While the skill mentions using tools like write_to_file and find_code, these are used in the context of standard architectural tasks and do not involve unsafe shell command execution or privilege escalation.

architecture