HOL Guard Security Atlas

A living map of what AI coding agents try to do.

Learn the risky patterns behind blocked commands, MCP tools, skills, plugins, and agent prompts. Every public warning is redacted before it teaches anyone else.

Redacted by default
No raw prompts
No private paths
Noindex until moderated

Start with the threat, not the jargon

Each guide begins with a plain-English explanation, then opens into deeper controls and examples.

Harness setup guides

Protect the coding tools your team already uses without forcing everyone to become a security expert.

Redacted warnings

Real protection moments, scrubbed for safety before becoming public learning pages.

Safe labs

Practice attack patterns with static simulations. Nothing dangerous executes.

Curated advisories

Only enriched explainers are indexable; raw CVE imports stay hidden until useful.