Nm Leyline Content Sanitization

Sanitization guidelines for external content

This is a guidelines-only skill (no code, no credentials) that sensibly describes how to sanitize external content. Before relying on it: 1) confirm your agent runtime actually implements the referenced PostToolUse hook (sanitize_external_content.py) or otherwise enforces these rules, because the skill does not include that implementation; 2) note the file header version (1.8.2) differs from registry version (1.0.0) — confirm which version you'll follow; 3) test the sanitization rules against adversarial inputs (zero-width chars, hidden HTML/CSS, obfuscated instruction patterns) to ensure your environment's implementation is robust; and 4) remember these are guidelines — they reduce risk but do not guarantee safety on their own.

Type: OpenClaw Skill Name: nm-leyline-content-sanitization Version: 1.0.0 The skill bundle consists of defensive guidelines and instructions designed to protect the OpenClaw agent from prompt injection and malicious code execution when handling external content. It outlines a comprehensive sanitization checklist in SKILL.md, including stripping XML-like system tags, instruction-override patterns, hidden CSS formatting, and zero-width characters, which are standard security best practices for LLM-based agents.