The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute local Python scripts (cms_detect.py and various preflight_*.py scripts) for detecting existing CMS configurations and validating user-provided credentials.
[SAFE]: Sensitive credential management (API keys, application passwords) is handled correctly by instructing the agent to write these values to a local .env.local file, which is the standard procedure for local secret management and avoids insecure persistence.
[SAFE]: The skill exhibits no signs of prompt injection, data exfiltration to unauthorized domains, or obfuscation; all external CMS URLs are provided by the user and used for the skill's primary setup purpose.

setup-cms