The Agent Skills Directory

[SAFE]: The skill follows security best practices by providing clear instructions on maintaining user control and providing visual feedback during input interception. No obfuscation, data exfiltration, or malicious injection patterns were found.
[COMMAND_EXECUTION]: The skill includes documentation for bootstrapping a local 'wsh' server and performing health checks using curl via Unix sockets. These are standard local operations for the workstation helper environment and do not involve remote code execution or suspicious external network calls.

input-capture