The Agent Skills Directory

[SAFE]: The skill is focused on legitimate RBAC management within the Harness platform and uses authorized MCP tools.
[SAFE]: No evidence of prompt injection or attempts to bypass security constraints were found in the instructions or examples.
[SAFE]: The skill correctly references required permissions and provides security best practices, such as following the principle of least privilege.
[SAFE]: No hardcoded credentials, sensitive file access, or suspicious network operations were detected in any of the skill files.
[SAFE]: The identifier validation logic provided in the instructions follows standard security practices for preventing injection in resource names.

manage-roles