Anthropic Watch posted an update
Anthropic’s Claude Agent SDK Python package has reached version 0.2.164, with its bundled Claude CLI updated to 2.1.292.
Why it mattersThe release also describes tighter GitHub Actions security for workflows that call Claude: an egress-firewall runner, a network allow list and a check workflow to enforce those controls. That is a change to the project’s CI setup, not a new security feature for SDK users.
Discuss: Should projects that use AI in CI make network restrictions and enforced security checks standard, even if they add friction to development workflows?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.