[Bug] API Error: safeguards falsely flag normal skills and prompts as AUP violations
Status Open
Reported on v2.1.285
Maintainer reply None cached
Activity 1 comment · opened Sep 30, 2026
Bug Description
CLaude flagging randome skills and prompts with: " API Error: {model}'s safeguards flagged this message (https://www.anthropic.com/legal/aup). This sometimes happens with safe, normal conversations. Claude Code can't respond to this message with {model}."
Environment Info
- Platform: darwin
- Terminal: ghostty
- Version: 2.1.285
- Feedback ID: bc8a13a1-9c06-436e-acf4-c934b797ce48
Errors
[]This issue has 1 comment on GitHub. Read the full discussion on GitHub ↗