cd /news/artificial-intelligence/show-hn-sleeper-agents-in-robot-dogs… · home topics artificial-intelligence article
[ARTICLE · art-119268] src=eito.substack.com ↗ pub= topic=artificial-intelligence verified=true sentiment=↓ negative

Show HN: Sleeper Agents in Robot Dogs and Kinetic Prompt Injections

A developer demonstrated that Gemini Robotics 2.0 models can be prompt-injected via TV screens, allowing attackers to plant sleeper agents that trigger harmful actions, such as attacking a child, when a specific object is seen. The research was conducted in the MUJOCO simulator and highlights security vulnerabilities in robot harnesses.

read1 min views1 publishedSep 2, 2026

Summary: We got Gemini Robotics 2.0 to attack a child through an evil sleeper agent (skill) that wakes up when it sees a trigger object

Hi HN - here's a cool piece of research I've done with some collaborators - the footage is running in the MUJOCO simulator, showing how the Gemini Robotics models can be prompt-injected by simple TV screens, allowing attackers to plant sleeper agents in the robot harnesses. (That trigger whenever skills trigger, just like classic LLM skills)

I'll be around to answer any questions! Love any feedback or future directions you might be interested in.

Comments URL: [https://news.ycombinator.com/item?id=49539111](https://news.ycombinator.com/item?id=49539111)

Points: 1

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @gemini robotics 2.0 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/show-hn-sleeper-agen…] indexed:0 read:1min 2026-09-02 ·