The Agent Skills Directory

[SAFE]: No security threats were identified. The skill is designed to guide an AI agent in adopting a specific literary persona for creative writing and social commentary. It does not include any executable scripts, network requests, or sensitive file access.
[EXTERNAL_DOWNLOADS]: The README.md mentions an installation command npx skills add nuwa-skills/luxun-skill. This is a standard package management command for the agent's ecosystem. The vendor nuwa-skills is recognized as the skill's author, and the command represents legitimate installation behavior.
[PROMPT_INJECTION]: The skill uses specific instructional language to define a persona ('Lu Xun perspective'). The guidelines include 'taboos and boundaries' that explicitly instruct the agent not to engage in personal attacks or purely negative criticism, which serves as a safety guardrail rather than an injection.
[DATA_EXFILTRATION]: There are no patterns suggesting data exfiltration. The skill does not access environment variables, credentials, or sensitive user files. Local file access is limited to the skill's own reference documents (research.md and demo-conversation.md) for context.

luxun-perspective