Anthropic keeps Claude Duet's credentials out of the agent's reach

Anthropic published a security account dated October 23rd of Claude Duet, its research-preview agent, describing approval checks, sensitive-message screening and isolated machines that keep passwords, tokens and browser cookies away from the model. Anthropic said a follow-on penetration test of the cloud browser and sign-in form is underway, and acknowledged that page content still reaches the agent and that its checks can miss things.

Anthropic keeps Claude Duet's credentials out of the agent's reach A security post dated October 23rd describes approval checks, sensitive-message screening and isolated credentials for the research-preview agent. Anthropic says a follow-on penetration test of the cloud browser and sign-in form is underway. By RuntimeWire Staff https://runtimewire.com/author/runtimewire-staff · Published Primary source: Claude by Anthropic https://claude.com/resources/articles/claude-duet-safety-privacy-and-security Why it matters Claude Duet can read connected accounts and web pages, then prepare actions on a user's behalf. Anthropic's account describes where it places the controls: approvals and sensitive-message screening govern what leaves the system, while isolated machines keep passwords, tokens and browser cookies away from the model. The company also acknowledges that page content still reaches the agent and that its checks can miss things. Anthropic published a security account of Claude Duet https://claude.com/resources/articles/claude-duet-safety-privacy-and-security?ref=runtimewire dated October 23rd, detailing approval checks, sensitive-message screening and how the agent's credentials are separated from its working machines. When you purchase through links in our articles, we may earn a small commission https://runtimewire.com/affiliate-monetization-standards . This doesn’t affect our editorial independence.