The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions for writing character dialogue. It does not include any scripts, command-line executions, or external dependencies.
[DATA_EXPOSURE]: The skill metadata requests file:read and file:write permissions. This is consistent with its purpose as a writing assistant that may need to access or modify manuscript files. No specific sensitive file paths or exfiltration patterns were detected.
[PROMPT_INJECTION]: The instructions focus on character voice and subtext. There are no attempts to override system prompts, bypass safety filters, or use adversarial role-play techniques.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to process user-provided character data, it serves as a set of stylistic guidelines for the AI. It does not provide automated mechanisms that would allow untrusted data to execute system commands or access sensitive information beyond the stated file permissions.

dialogue