The Agent Skills Directory

[NO_CODE] (SAFE): This skill contains no executable scripts, shell commands, or external dependencies. It is entirely composed of markdown instructions and diagnostic frameworks.- [DATA_EXFILTRATION] (SAFE): There are no network requests, API calls, or interactions with the file system. User input is limited to answering diagnostic questions within the chat context.- [REMOTE_CODE_EXECUTION] (SAFE): No external scripts are downloaded or executed. The skill does not use package managers or dynamic code loading.- [PROMPT_INJECTION] (SAFE): The instructions follow standard instructional patterns for marketing automation. There are no attempts to override safety filters or extract system prompts.- [COMMAND_EXECUTION] (SAFE): While the skill mentions using commands like /brand-voice, these refer to internal AI agent skill invocations within a controlled environment, not operating system level commands.

orchestrator