Wanxiang Scroll Tools

万象绘卷工具与安全分卷 - 包含实用工具、安全防御、拆书融合、小说分析

This skill is mostly writing tools plus a security chapter and can be useful for creative work and guidance on prompt-injection defenses. Before installing or following its 'deployment' steps, consider: 1) Do NOT blindly write the suggested AGENTS.md / SOUL.md / IDENTITY.md into your agent workspace — review their full text and understand consequences. 2) Backup ~/.openclaw/workspace/ (or equivalent) before making any changes. 3) Prefer applying rules manually or in a sandboxed test agent first; avoid making persistent, high-priority config changes until you trust the source. 4) If you want the security guidance, read the docs and implement the controls yourself rather than auto-applying 'highest-priority' persona files. 5) If anything is unclear, ask the skill author for provenance and why persistent workspace changes are required.

Type: OpenClaw Skill Name: wanxiang-scroll-tools Version: 1.0.0 The skill bundle is a comprehensive set of tools and guidelines for a creative writing and interactive storytelling framework called 'Wanxiang Scroll'. The most notable feature is Chapter 09, which contains detailed 'security' instructions; however, these are defensive in nature, providing the AI agent with strategies to resist prompt injection, maintain mode isolation (Creation vs. Interactive), and detect malicious user attempts to bypass game logic. There is no evidence of data exfiltration, unauthorized system access, or malicious code execution; the bundle focuses entirely on enhancing the role-playing experience and providing structured writing workflows like the 'Book Fusion' method.