Perimeter-Level Access Control (OpenClaw)
- Entity ID:
ent-20260423-p3a000000002 - Type:
pattern - Scope:
private - Status:
active
Description
OpenClaw's trust architecture: rather than evaluating safety per tool-invocation like Claude Code, OpenClaw places the trust boundary at the gateway perimeter using DM pairing codes, sender allowlists, and gateway authentication, with tool policy as configurable allow/deny lists per agent. Sandboxing (Docker/SSH/OpenShell backends) is opt-in and explicitly does not claim hostile multi-tenant isolation as a supported security boundary.
Key claims
- Claude Code vs OpenClaw: per-action vs perimeter safety
- Opposite bets follow from different trust models and deployment topologies
Relations
- OpenClaw --[contains]--> Perimeter-Level Access Control (OpenClaw)
- Perimeter-Level Access Control (OpenClaw) --[contrasts_with]--> Architectural Convergence Thesis