anthropics / anthropics/claude-code

[Bug] Anthropic API Error: Overly broad cybersecurity safety filter triggering on non-security topics

Open
#94,615 0 comments 0 reactions 0 assignees View on GitHub
api:anthropic area:model area:security bug duplicate platform:macos
Dominant language
Python
Stars
145k
Forks
23.1k
PR merge metrics
PR metrics pending

Description

**Bug Description**
API Error: Sonnet 5 has safety measures that flagged this message for a cybersecurity topic. To learn about the Cyber Verification Program and apply for access, visit our help center: https://support.claude.com/en/articles/14604842-real-time-cyber-safeguards-on-claude.

If you were not engaging in a cybersecurity topic, please send feedback via /feedback.

Request ID: req_011Cf66by1PesSRrchhwEhyv getting this error even after not seraching cybersecuritrty related topics

**Environment Info**
- Platform: darwin
- Terminal: Apple_Terminal
- Version: 2.1.207
- Feedback ID: 3a7132f4-c27b-46ba-ab36-b2c6b9ac19b1

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

Contributor guide

No contributing guide indexed for this repository

Research direction

No repository files, tests, or code entry points are named. Start by reproducing the reported Anthropic API safety-filter error using the supplied platform, request ID, and feedback ID; done means establishing whether a non-cybersecurity request is being rejected and recording a confirmed resolution or escalation.

Written by the indexing model from the issue text.

Assessment

Domain
api, security
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.