feat: add security guides and sanitize external links across repo

New articles:
- the-security-guide.md: "The Shorthand Guide to Securing Your Agent" (595 lines)
  Attack vectors, sandboxing, sanitization, OWASP Top 10, observability
- the-openclaw-guide.md: "The Hidden Danger of OpenClaw" (470 lines)
  Security analysis of OpenClaw, MiniClaw thesis, industry evidence

External link sanitization (22 files across EN, zh-CN, zh-TW, ja-JP, .cursor):
- Removed third-party GitHub links from skills and guides
- Replaced with inline descriptions to prevent transitive prompt injection
- Kept official org links (Anthropic, Google, Supabase, Mixedbread)

docs/zh-TW/README.md

@@ -464,7 +464,7 @@ node tests/hooks/hooks.test.js
 - **完整指南（進階）：** [Everything Claude Code 完整指南](https://x.com/affaanmustafa/status/2014040193557471352)
 - **追蹤：** [@affaanmustafa](https://x.com/affaanmustafa)
 - **zenith.chat：** [zenith.chat](https://zenith.chat)
-- **技能目錄：** [awesome-agent-skills](https://github.com/JackyST0/awesome-agent-skills)
+- **技能目錄：** awesome-agent-skills（社區維護的智能體技能目錄）
 
 ---
 

docs/zh-TW/skills/continuous-learning-v2/SKILL.md

@@ -249,7 +249,7 @@ v2 完全相容 v1：
 ## 相關
 
 - [Skill Creator](https://skill-creator.app) - 從倉庫歷史產生本能
-- [Homunculus](https://github.com/humanplane/homunculus) - v2 架構靈感
+- Homunculus - 啟發 v2 架構的社區專案（原子觀察、信心評分、本能演化管線）
 - [Longform Guide](https://x.com/affaanmustafa/status/2014040193557471352) - 持續學習章節
 
 ---

docs/zh-TW/skills/continuous-learning/SKILL.md

@@ -83,7 +83,7 @@ description: Automatically extract reusable patterns from Claude Code sessions a
 
 ## 比較筆記（研究：2025 年 1 月）
 
-### vs Homunculus (github.com/humanplane/homunculus)
+### vs Homunculus
 
 Homunculus v2 採用更複雜的方法：