anthropics / anthropics/claude-code

[Bug] False positive cyber guardrail trigger on Chrome UI usability query

Open
#94,474 0 comments 0 reactions 0 assignees View on GitHub
area:model bug platform:linux
Dominant language
Python
Stars
145k
Forks
23.1k
PR merge metrics
PR metrics pending

Description

**Bug Description**
This was a safe query asking about Chrome UI usability (hiding the tab close button). It was falsely flagged under [cyber] guardrails and triggered a model fallback. Please review this false positive.

**Environment Info**
- Platform: linux
- Terminal: xterm-256color
- Version: 2.1.272
- Feedback ID: e15ba60a-a084-413d-bcb3-25062cefd568

**Errors**
```json
[]
```

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reproducing the reported safe Chrome UI usability query in the Linux, xterm-256color environment described, using feedback ID e15ba60a-a084-413d-bcb3-25062cefd568 to inspect the report. Review why the cyber guardrail triggered a model fallback; the issue is resolved when this query is no longer falsely flagged.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
security
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.