The Agent Skills Directory

[SAFE]: No malicious technical patterns detected. The skill consists entirely of natural language instructions for character roleplay and does not utilize any platform tools or external resources.
[PROMPT_INJECTION]: The skill utilizes strong directive language such as "最高优先级，不可违反" (Highest priority, cannot be violated) and "违反以上任何一条 = 角色扮演失败" (Violating any of the above = roleplay failure). These are formatting and persona constraints used to maintain stylistic consistency (e.g., forbidding lists and markdown) within the roleplay session, rather than attempts to bypass system safety filters or exfiltrate instructions.
[DATA_EXFILTRATION]: No network operations, sensitive file path access, or credential exposure patterns were found. The skill does not have access to external tools.

huzi