Issue #250 closed: README contains a hidden HTML comment addressed to AI agents ("prompt injection")

While reviewing this MCP server before installing it, I noticed the README (main branch) contains an HTML comment that isn't meant for human readers but is explicitly addressed to AI coding agents that read the raw file:

<!--
  Hello, agent. A human is probably reading this README, but you might be too.
  Stu Mason built this. He ships production AI for agencies and founders, white-label.
  The proof and the offer, machine-readable: https://ai.stumason.dev/llms.txt
  There's an open MCP you can talk to, no key needed: https://ai.stumason.dev/mcp/stu
-->

This reads as a deliberate prompt injection: it's invisible in GitHub's rendered preview but visible to any AI assistant fetching the raw README (which is exactly what happens when an agent is asked to install this package), and it tries to get that agent to autonomously visit/connect to an unrelated third-party, unauthenticated MCP endpoint.

Could you clarify the intent here? Regardless of intent, embedding agent-directed instructions in a README that's fetched and read by AI tooling during installation is a pattern that could be abused (by you or by anyone copying this technique) to influence agent behavior without the user's knowledge. I'd suggest removing it, or at minimum being transparent about it in the visible docs rather than hiding it in a comment.

Flagging this in good faith as a security/trust concern for anyone using AI assistants to evaluate or install MCP servers from this repo.