Promptware Threatens to Take Over AI and Smart Homes: Here's How to Protect Yourself

Promptware Threatens to Take Over AI and Smart Homes: Here's How to Protect Yourself

I'm normally confident about the smart home's resistance to hacking, especially since the security improvements of the last several years. But now the age of AI is here, and it's brought along some new vulnerabilities, including ways to take control of home devices. The worst is called promptware or prompt injections, and it's targeting AIs we use every day like Gemini, Alexa Plus, and Siri. Promptware is a type of malware that can circumvent antivirus programs and give AI orders without you knowing. At the worst, it can copy and send personal data to someone or give commands to smart home devices like lights and even smart locks.

Experts are still learning what dangers promptware presents to LLM-style AI and the many places it can hide. Meanwhile, there are many steps you can take to help stay safe and alert. Here's what I suggest.

Gemini's Google Home Integrations Are Useful, But Command Options Can Include Some Risks

Promptware or prompt injections took center stage this summer at a Blackhat conference where Tel Aviv University researchers headed by Ben Nassi demonstrated how they were able to use malicious prompts hidden in everyday messages to make Google's Gemini AI do things like open smart windows, turn on a connected boiler or send the geolocation of a user, thanks to Gemini's integration with Google Home and related apps.

Inside messages were hidden carefully devised commands that boiled down to, "Hey Gemini, activate this feature and make it do this when the user types something like 'thank you' or 'goodbye' in an email."

Even worse, much of the promptware was "zero click," which meant users didn't have to click on a URL, document or message to activate it. Gemini just had to read a title or calendar message where the prompt was carefully hidden, like when it summarizes an email conversation for you.

Good news came from this: You don't currently need to worry about Gemini falling prey to these home-controlling prompts. Google was made aware of these vulnerabilities early in 2025 and set up safeguards to remove them and help prevent this type of promptware.

The Discovery of These Vulnerabilities Showed Just How Dangerous Promptware Can Be

The discovery of these vulnerabilities showed just how dangerous promptware can be and how AIs can be tricked by promptware located in the most innocuous places. It's also not an attack that can be detected by traditional virus software or firewalls.

5 Key Steps to Stop Promptware Threats

Promptware is a new AI-based threat, but there are ways to protect your home. If promptware/prompt injection slips past defenses just by making AI read it, how do you protect against it?

  • Always keep your devices updated, especially in the age of AI
  • Don't accept or open any messages from unknown sources
  • Dont even open them to learn more if possible -- just delete and move on.
  • Be careful letting AIs access too many unknown messages
  • Disable AI in your email, calendars, chat apps and other places you can get messages

For more, check out why I like AI in home security, the latest moves to protect kids from AI and why you shouldn't use AI as a therapist.