The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses subprocess to invoke standard macOS developer utilities such as xctrace, otool, vmmap, and atos. These calls are implemented using argument lists, which is a secure practice to prevent shell injection.
[DATA_EXPOSURE]: Performance traces and extracted XML data are stored and processed locally in the /tmp/ directory. No network operations or external data exfiltration patterns were identified.
[SAFE]: The scripts are clearly written for the stated purpose of performance analysis. They use standard Python and Bash practices without any signs of obfuscation, persistence mechanisms, or unauthorized privilege escalation.

native-app-performance