Security audit
Security checks for vulnerabilities and agentic risk
This Slack plugin is a disclosed channel integration that uses Slack credentials to receive and send configured workspace messages, with some high-impact Slack actions that are documented and configurable.
Install only if you want OpenClaw connected to a Slack workspace. Use least-privilege Slack app scopes, prefer bot tokens over user tokens, keep DM and channel allowlists narrow, and review settings for message deletes, pins, native commands, exec approvals, and proactive rich replies before enabling them in shared channels.
The manifest description contains very broad auto-trigger phrases such as any Slack UI component mention, the words "blocks" or "Block Kit Builder," and even pasted JSON patterns. This can cause the skill to activate outside its intended scope, potentially hijacking unrelated Slack conversations or code-review contexts and steering the agent into this skill unnecessarily.
The skill description and body instruct the agent to use this capability proactively for broad classes of Slack replies, which can cause the skill to activate in situations where the user did not explicitly request structured Slack output. Overly broad activation increases the chance of unintended tool use, unnecessary message sending, or accidental delivery of rich interactive content into Slack channels.
No suspicious patterns detected.
