The Agent Skills Directory

[SAFE]: The skill is authored by Harness and utilizes official vendor resources, including the harness-mcp-v2 server and associated tools. No malicious patterns, prompt injections, or unauthorized data access attempts were detected.
[COMMAND_EXECUTION]: The skill utilizes harness_list and harness_execute to interact with the Harness platform. These operations are strictly scoped to the management of security exemptions as described in the skill's purpose and are mediated by the platform's role-based access control (RBAC).
[EXTERNAL_DOWNLOADS]: No external dependencies, scripts, or remote code patterns are present. All operations occur within the trusted platform environment.

approve-exempt