The Agent Skills Directory

[SAFE]: The skill contains extensive biographical and philosophical documentation intended to guide an AI in emulating a specific persona. The instructions are purely descriptive and instructional regarding tone and perspective.- [PROMPT_INJECTION]: Although the skill provides strong directives on how the agent should behave and think (e.g., 'assume the cognitive structure... of Steve Jobs'), these are standard for persona-based skills and do not attempt to bypass system safety constraints or extract internal prompts.- [DATA_EXFILTRATION]: No evidence of sensitive file access, credential harvesting, or network operations to external domains was found. The skill does not request or handle user secrets.- [COMMAND_EXECUTION]: The skill does not contain any shell commands, scripts, or instructions for the agent to execute code in the user's environment. The tools listed in the frontmatter are standard CLI interfaces, and their inclusion in the configuration serves to scope the agent's environment rather than execute malicious actions.

steve-jobs