By Vero SecurityBuilt and funded by Vero Security, the AI Security Engineering platform.Read the charter

Computer-use and browser agents

Computer-use agents operate a desktop or browser the way a person does, reading screenshots and issuing clicks and keystrokes. Because they read arbitrary pages and act inside logged-in sessions, they face the hardest version of prompt injection. Vendors pair them with classifiers, confirmations, and isolation.

Read in this order

  1. PaperWASP: Benchmarking Web Agent Security Against Prompt Injection AttacksStart here: a benchmark showing how often web agents follow injected instructions.
  2. ArticleComputer-Using Agent (OpenAI)How one vendor built a computer-using agent and what safeguards it ships.
  3. ArticleIntroducing computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku (Anthropic)The launch of computer use, including the safety caveats at the time.

Save your progress

We email you a sign-in link. No password.

By signing in you agree to the terms. The privacy policy explains how we use your details.

Join the AI security engineering community

Free. Roadmap updates, chapters near you, and first word when credentials open.

We’ll email you community updates. Unsubscribe anytime. By sending this you agree to the terms. The privacy policy explains how we use your details.