The Agent Skills Directory

[SAFE]: The skill does not contain any malicious patterns such as prompt injection, data exfiltration, or persistence mechanisms.
[COMMAND_EXECUTION]: The Python scripts in the scripts/ directory use subprocess.run to call macOS system utilities like networksetup, ifconfig, airport, and notifyutil. These calls use argument lists rather than shell strings and do not incorporate user-provided input, which effectively prevents command injection attacks.
[DATA_EXFILTRATION]: The skill accesses local network metadata including IP addresses and MAC addresses. However, it lacks any network capabilities (like curl or requests) to transmit this information to external domains.

osascript-network