The Agent Skills Directory

[SAFE]: The skill provides instructional content and two scripts, lighthouse_check.js and lighthouse_check.py. Both scripts are safe, containing only console output of hardcoded strings and no interaction with the network, file system, or system commands.
[COMMAND_EXECUTION]: The SKILL.md documentation includes a protocol for running a local Python script for performance checks. The command targets a local file distributed with the skill and executes no dangerous logic.
[DATA_EXFILTRATION]: There is no evidence of hardcoded credentials, sensitive file path access, or unauthorized network operations across any of the files.

performance-engineer