Threat explainer

Workspace trust boundaries

How AI agents cross workspace boundaries — reading other projects, team configs, and monorepo secrets.

AI tools can see files outside your project. That can leak data across teams.

Workspace trust boundary violations occur when an agent reads files from adjacent projects, shared monorepo configs, or team-wide credentials that fall outside its intended task scope.

HOL Guard turns these moments into private receipts first, then public lessons only after redaction and moderation.

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.