The Agent Skills Directory

[SAFE]: The skill provides usage guidelines for the Multica CLI to manage automations. It includes explicit safety instructions for redacting secrets and avoiding unintended side effects.
[COMMAND_EXECUTION]: The skill is restricted to using the multica CLI via the allowed-tools configuration. The instructions are declarative and do not contain shell injection vectors or arbitrary command execution patterns.
[DATA_EXFILTRATION]: No exfiltration patterns were detected. The skill manages internal vendor resources and provides specific guidance to the agent on redacting sensitive output, such as webhook tokens, to prevent accidental disclosure.
[CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or sensitive local configuration files are referenced. The technical documentation provided in the references confirms that sensitive fields are redacted by the server based on ownership and authorization levels.

multica-autopilots