diff --git a/docs/gateway/security/index.md b/docs/gateway/security/index.md
index d534143b1d4..bade7757360 100644
--- a/docs/gateway/security/index.md
+++ b/docs/gateway/security/index.md
@@ -90,6 +90,7 @@ Treat Gateway and node as one operator trust domain, with different roles:
 - A caller authenticated to the Gateway is trusted at Gateway scope. After pairing, node actions are trusted operator actions on that node.
 - `sessionKey` is routing/context selection, not per-user auth.
 - Exec approvals (allowlist + ask) are guardrails for operator intent, not hostile multi-tenant isolation.
+- OpenClaw's product default for trusted single-operator setups is that host exec on `gateway`/`node` is allowed without approval prompts (`security="full"`, `ask="off"` unless you tighten it). That default is intentional UX, not a vulnerability by itself.
 - Exec approvals bind exact request context and best-effort direct local file operands; they do not semantically model every runtime/interpreter loader path. Use sandboxing and host isolation for strong boundaries.
 
 If you need hostile-user isolation, split trust boundaries by OS user/host and run separate gateways.
@@ -173,6 +174,7 @@ If more than one person can DM your bot:
 - **Inbound access** (DM policies, group policies, allowlists): can strangers trigger the bot?
 - **Tool blast radius** (elevated tools + open rooms): could prompt injection turn into shell/file/network actions?
 - **Exec approval drift** (`security=full`, `autoAllowSkills`, interpreter allowlists without `strictInlineEval`): are host-exec guardrails still doing what you think they are?
+  - `security="full"` is a broad posture warning, not proof of a bug. It is the chosen default for trusted personal-assistant setups; tighten it only when your threat model needs approval or allowlist guardrails.
 - **Network exposure** (Gateway bind/auth, Tailscale Serve/Funnel, weak/short auth tokens).
 - **Browser control exposure** (remote nodes, relay ports, remote CDP endpoints).
 - **Local disk hygiene** (permissions, symlinks, config includes, “synced folder” paths).
@@ -375,6 +377,7 @@ If a macOS node is paired, the Gateway can invoke `system.run` on that node. Thi
 - The Gateway applies a coarse global node command policy via `gateway.nodes.allowCommands` / `denyCommands`.
 - Controlled on the Mac via **Settings → Exec approvals** (security + ask + allowlist).
 - The per-node `system.run` policy is the node's own exec approvals file (`exec.approvals.node.*`), which can be stricter or looser than the gateway's global command-ID policy.
+- A node running with `security="full"` and `ask="off"` is following the default trusted-operator model. Treat that as expected behavior unless your deployment explicitly requires a tighter approval or allowlist stance.
 - Approval mode binds exact request context and, when possible, one concrete local script/file operand. If OpenClaw cannot identify exactly one direct local file for an interpreter/runtime command, approval-backed execution is denied rather than promising full semantic coverage.
 - If you don’t want remote execution, set security to **deny** and remove node pairing for that Mac.