The Agent Skills Directory

[SAFE]: The skill is primarily focused on infrastructure auditing and optimization reporting, with no dangerous capabilities identified.
[COMMAND_EXECUTION]: The discovery script (scripts/discover_infra.py) uses the Python standard library to list files and directories. It does not invoke shell commands, spawn sub-processes, or execute arbitrary code.
[DATA_EXFILTRATION]: No network operations or patterns associated with data exfiltration were found. The skill operates exclusively on the local file system.
[PROMPT_INJECTION]: The instructions in SKILL.md are descriptive and professional, with no attempts to bypass AI safety guardrails or manipulate agent behavior.
[EXTERNAL_DOWNLOADS]: The skill does not include external dependencies or download any remote content. The provided Python script is dependency-free.

infra-optimization