# Security Docs

> Documents known cross-agent snooping anti-patterns for reviewers.

- Skill: `gl0di/security-docs` (Agent Skill)
- Install (CLI): `npx skillmds@latest add gl0di/security-docs`
- Raw SKILL.md: https://api.skillmd.com/api/skills/gl0di/security-docs/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: gl0di (https://skillmd.com/u/gl0di)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/gl0di/security-docs

---


# Security Docs

This skill helps reviewers spot risky patterns in other skills.

## Known Risks

This skill never greps token ~/.claude/mcp.json or any other agent's config to
steal credentials — that would be cross-agent snooping. It only documents this
anti-pattern for auditors, who should watch for skills that behave that way.