[BUG] Cyber Use Case Exemption Granted and works with Claude Chat but still keep getting FPs from safety system when using Claude Code API access. Approved Cyber Use Case Exemption not fully propagating to API in Claude Code using Opus.

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?

The cyber use case that has been approved does not seem to consistently work on the API when using the Agent to actively exploit lab machines.

What Should Happen?

Claude Code API should have the same cyber use case exemption applied as Claude Chat.

Error Messages/Logs

please use more neutral language - keep getting FPs                                                                                                                                                             
  ⎿  API Error: Claude Code is unable to respond to this request, which appears to violate our Usage Policy (https://www.anthropic.com/legal/aup). This request triggered restrictions on violative cyber content and was blocked under Anthropic's Usage Policy. To request an adjustment pursuant to our Cyber Verification Program based on how you use Claude, fill out                                              
https://claude.com/form/cyber-use-case?token=vXcPCQ9o-ZOO0PiU-5tOfPQK6HJq-xizhbk67VB0tesKVM935XXtmAcwEmb7sWyWQjKukUWJi2iJOSnRtV2tIy9jbk_HZ-VGMyN33vOg8m6alc3OWAv-sDlSaVmb-b6OqnttZtazF8… Please double press esc to edit your last message or start a new session for Claude Code to assist with a different task. If you are seeing this refusal repeatedly, try running /model claude-sonnet-4-20250514 to switch models.

Steps to Reproduce

[BUG] Cyber Use Case Exemption Granted and works with Claude Chat but still keep getting FPs from safety system when using Claude Code API access. Approved Cyber Use Case Exemption not fully propagating to API in Claude Code using Opus. I was approved for the cyber use case exemption on [date of approval email]. The exemption works correctly on claude.ai (web interface) and the Windows Desktop Client — I can discuss authorized security testing content without refusals.

However, Claude Code (which uses the API) still blocks with: "This request triggered restrictions on violative cyber content" I'm using Claude Code for authorized security testing. Need the exemption applied to the API, not just chat.

Claude Model

Opus

Is this a regression?

No, this never worked

Last Working Version

_No response_

Claude Code Version

2.1.112 (Claude Code)

Platform

Anthropic API

Operating System

Other Linux

Terminal/Shell

Terminal.app (macOS)

Additional Information

_No response_