The Agent Skills Directory

[SAFE]: The skill consists exclusively of Markdown-based instructions and local resource files designed to guide the agent in narrative writing tasks.
[REMOTE_CODE_EXECUTION]: No remote code execution patterns or dynamic code generation were detected. The skill relies entirely on natural language instructions and local JSON/Markdown resources.
[DATA_EXFILTRATION]: No network operations, API calls, or sensitive file path references (e.g., credentials, environment variables) were identified.
[EXTERNAL_DOWNLOADS]: The skill does not attempt to download external scripts, packages, or configuration files from remote servers.
[PROMPT_INJECTION]: The instructions contain strict constraints and rubrics to guide agent behavior for narrative quality, but no attempts to override safety filters or bypass system instructions were detected.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to process external data (a 'researched corpus'), it lacks any tools or capabilities (like shell execution or network access) that could be exploited by malicious content within that data.

systemic-protagonist