[BUG] Opus 5.5 throws cyber safeguard to even a simple prompt with nothing unsafe

Preflight Checklist

• [x] I have searched existing issues and this hasn't been reported yet
• [x] This is a single bug report (please file separate reports for different bugs)
• [x] I am using the latest version of Claude Code

What's Wrong?

Latest Claude version throws safeguards to a simple "hello" prompt. It is not responding at all.

What Should Happen?

It is supposed to work normally unless there is a real cyber prompt

Error Messages/Logs

API Error: Opus 5.5 (1M context)'s safeguards flagged this session (https://www.anthropic.com/legal/aup). You may be seeing this for the first time on an Opus model: Opus 5.5 (1M context) is more capable and has stronger safeguards as a result, which can sometimes flag non-cybersecurity work. We're improving these safeguards to reduce the amount of incorrectly flagged messages. Claude Code can't respond to your last message with Opus 5.5 (1M context).

  Double press esc to edit your last message, or try a different model with /model.

  Send feedback with /feedback or learn more: https://support.claude.com/en/articles/8106465

  Details: `[cyber]`

  Request ID: req_011CfMBbwqLFHzBaTgKQspyd

Steps to Reproduce

<img width="1463" height="460" alt="Image" src="https://github.com/user-attachments/assets/adcbe9f7-2a10-4cfc-9541-eb5489316c4c" />

Claude Model

Opus 5.5

Is this a regression?

Yes, this worked in a previous version

Last Working Version

v2.1.281

Claude Code Version

v2.1.281

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Other

Additional Information

Feedback ID: a15c2d01-7089-488f-86b8-5d46d59e3151
platform: Ghostty, darwin
Macos