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)

skills/continuous-learning-v2/SKILL.md

@@ -285,7 +285,7 @@ v2 is fully compatible with v1:
 ## Related
 
 - [Skill Creator](https://skill-creator.app) - Generate instincts from repo history
-- [Homunculus](https://github.com/humanplane/homunculus) - Inspiration for v2 architecture
+- Homunculus - Community project that inspired the v2 instinct-based architecture (atomic observations, confidence scoring, instinct evolution pipeline)
 - [The Longform Guide](https://x.com/affaanmustafa/status/2014040193557471352) - Continuous learning section
 
 ---

skills/continuous-learning/SKILL.md

@@ -92,7 +92,7 @@ Add to your `~/.claude/settings.json`:
 
 ## Comparison Notes (Research: Jan 2025)
 
-### vs Homunculus (github.com/humanplane/homunculus)
+### vs Homunculus
 
 Homunculus v2 takes a more sophisticated approach:
 

skills/nutrient-document-processing/SKILL.md

@@ -162,5 +162,4 @@ For native tool integration, use the MCP server instead of curl:
 
 - [API Playground](https://dashboard.nutrient.io/processor-api/playground/)
 - [Full API Docs](https://www.nutrient.io/guides/dws-processor/)
-- [Agent Skill Repo](https://github.com/PSPDFKit-labs/nutrient-agent-skill)
 - [npm MCP Server](https://www.npmjs.com/package/@nutrient-sdk/dws-mcp-server)