The Agent Skills Directory

[SAFE]: Detailed analysis of the skill content and instructions confirms that the functionality aligns with the stated purpose of performance profiling with no evidence of malicious intent.
[COMMAND_EXECUTION]: The script scripts/lighthouse_audit.py executes the lighthouse command-line utility. The implementation uses the subprocess.run method with an argument list rather than a shell string, which is a security best practice that prevents shell injection vulnerabilities.
[EXTERNAL_DOWNLOADS]: The skill references the lighthouse CLI tool, which is a well-known service provided by Google. The skill does not automate the installation of this dependency or download code from untrusted or unknown sources.

performance-profiling