docs: clarify exec defaults

docs/gateway/security.md

@@ -211,7 +211,7 @@ Even with strong system prompts, **prompt injection is not solved**. What helps
 - Prefer mention gating in groups; avoid “always-on” bots in public rooms.
 - Treat links, attachments, and pasted instructions as hostile by default.
 - Run sensitive tool execution in a sandbox; keep secrets out of the agent’s reachable filesystem.
-- Note: sandboxing is opt-in; if sandbox mode is off, exec runs on the gateway host even though tools.exec.host defaults to sandbox.
+- Note: sandboxing is opt-in. If sandbox mode is off, exec runs on the gateway host even though tools.exec.host defaults to sandbox, and host exec does not require approvals unless you set host=gateway and configure exec approvals.
 - Limit high-risk tools (`exec`, `browser`, `web_fetch`, `web_search`) to trusted agents or explicit allowlists.
 - **Model choice matters:** older/legacy models can be less robust against prompt injection and tool misuse. Prefer modern, instruction-hardened models for any bot with tools. We recommend Anthropic Opus 4.5 because it’s quite good at recognizing prompt injections (see [“A step forward on safety”](https://www.anthropic.com/news/claude-opus-4-5)).
 

docs/tools/exec.md

@@ -34,6 +34,9 @@ Notes:
 - If multiple nodes are available, set `exec.node` or `tools.exec.node` to select one.
 - On non-Windows hosts, exec uses `SHELL` when set; if `SHELL` is `fish`, it prefers `bash` (or `sh`)
   from `PATH` to avoid fish-incompatible scripts, then falls back to `SHELL` if neither exists.
+- Important: sandboxing is **off by default**. If sandboxing is off, `host=sandbox` runs directly on
+  the gateway host (no container) and **does not require approvals**. To require approvals, run with
+  `host=gateway` and configure exec approvals (or enable sandboxing).
 
 ## Config