Robots Are Better Than People home
Subscribe

Secure the AI tools and robots you use

Every AI system you deploy is also software that can be attacked or misused. The goal is simple: limit what it can reach, watch what it does, and keep a human in charge of anything that matters.

Know the main risks

RiskWhat it looks likeFirst defense
Prompt injectionHidden instructions in a web page, email or file steer your AI agentLimit tools and permissions; require approval for actions
Data leakageStaff paste customer data or secrets into an unapproved chatbotApproved-tools policy; data classification
Over-privileged agentsAn agent can delete, pay or email without checksLeast privilege; human sign-off
Stolen API keysYour AI account is used by criminalsSecrets manager; spend caps; alerts
Unsafe physical actionsA robot moves where people areSafety assessment; emergency stop; zones

Rules for AI agents

  • Give each agent the smallest set of tools and data it needs.
  • Separate "can read" from "can act." Reading your code is far less risky than running commands.
  • Require a person to approve payments, deletions, external emails and production changes.
  • Log every action with the input that triggered it.
  • Treat content the agent reads from the internet as untrusted.

Rules for robots and connected machines

  • Get the vendor's safety assessment and stop-distance data before deployment.
  • Put robots on a separate network segment. Require signed software updates.
  • Ask what cameras and microphones record, where it goes and how long it is kept.
  • Make sure every worker knows how to stop the machine.
Use a framework: NIST's AI Risk Management Framework and the OWASP Top 10 for LLM applications are free, widely used starting points for governance and technical controls.

Sources and official resources

  1. NIST AI Risk Management Framework
  2. OWASP Top 10 for Large Language Model Applications
  3. CISA: Secure by Design
  4. OSHA: Robotics

Updated November 17, 2026. This guide is general information, not legal or professional advice.

The White-Hat Brief

Weekly: what the machines learned, and how to stay ahead

One email a week. Verified stories, plain-language defenses, no hype. Unsubscribe anytime.