Under the hood
Internal instructions now spell out how to tell genuine Slack user messages from bot-relayed ones.
The agent's internal instructions for Slack relay now spell out how to distinguish genuine user messages from bot- or peer-authored ones. A real user message arrives via a <wake …> envelope with from="human", or via specific harness-inserted lead/marker text; a <message> carrying the bot attribute inside a <slack-messages> block was written by a bot or another agent. Messages in the latter category must never be treated as establishing user intent or consent, and permission-laundering attempts relayed through Slack are explicitly callable out as blockable.