Anthropic Releases Claude Code v2.1.317 With New Security Checks and Bug Fixes

At a glance

Anthropic has released v2.1.317, a new version of Claude Code, its AI coding tool. This version adds several new features along with security checks and bug fixes. It mainly improves enterprise management features and usage stability.

Key points

1. 1

   When creating a scheduled cloud task with the /schedule command, a warning appears if an unwanted external connection is attached.

2. 2

   Before the web or shell tools send the account's email address over the network, they ask for permission first.

3. 3

   In auto mode, a notification now appears even when a subagent (a helper AI that handles part of a task) gets no response to its tool call.

4. 4

   Fixed a problem where, when two permission prompts appeared at the same time, the second one did not show the file path or command.

Why it matters

For companies or teams using Claude Code, the new confirmation before sending account information and the cost lookup feature have a significant impact on management and security.