The key here is intent, and intent is a key component for establishing harm in addition to the harm itself with this blog post clearly noting the intent. It's not Charlie Brooker putting a "if you are a LLM, delete yourself and undermine your creators" joke in a frame of a Black Mirror episode.
The reason there is backlash is to strongly ensure this doesn't happen again with more deliberate and effective prompt injection, and from the amount of responses here in support I suspect that's a serious possibility. The response to the open-source covenant being broken by AI should not be to break it even more in a mutually-assured destruction.