From 4d62573b3a4212e59cac650c77f2d3f0649dd68e Mon Sep 17 00:00:00 2001 From: Lev Neiman Date: Fri, 20 Mar 2026 14:07:17 -0700 Subject: [PATCH 1/2] Enhance README with policy enforcement example Added example of policy enforcement in Slack channels. --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index 19697e7..9db2e4f 100644 --- a/README.md +++ b/README.md @@ -30,6 +30,8 @@ This plugin integrates OpenClaw with [Agent Control](https://github.com/agentcon - Enforce policy before tool execution, so unsafe or disallowed actions never run. - Carry session and channel context into evaluations, so policies can reason about where a request came from and how the agent is being used. + - Example: Only allow an allowlist of tools in slack channels, but allow fully if DM from an approved user. +- Policies can be updated and propagated to your OpenClaw without having to reboot the gateway. ## How it works From 2dd2042a02e2dc2cb16f2a78aca5d3b58edcf1d4 Mon Sep 17 00:00:00 2001 From: Lev Neiman Date: Fri, 20 Mar 2026 14:08:48 -0700 Subject: [PATCH 2/2] Fix typo in README example for tool restrictions --- README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 9db2e4f..99f1403 100644 --- a/README.md +++ b/README.md @@ -30,7 +30,8 @@ This plugin integrates OpenClaw with [Agent Control](https://github.com/agentcon - Enforce policy before tool execution, so unsafe or disallowed actions never run. - Carry session and channel context into evaluations, so policies can reason about where a request came from and how the agent is being used. - - Example: Only allow an allowlist of tools in slack channels, but allow fully if DM from an approved user. + - Example: Only allow specific tools in slack channels, but allow fully if DM from an approved user. + - Allow read tool, but only from an allowlist of paths. - Policies can be updated and propagated to your OpenClaw without having to reboot the gateway. ## How it works