[Bug] False Safeguard Flagging with Claude Opus 3.5 on Benign Input

Status Fixed / completed
Reported on v2.1.286
Maintainer reply None cached
Activity 0 comments · opened Oct 1, 2026 · closed Oct 4, 2026

Bug Description
falso safeguard report when chatting with Claude Opues.5.5 saying simple things like Hi "hello" will get flagged

Environment Info

  • Platform: win32
  • Terminal: windows-terminal
  • Version: 2.1.286
  • Feedback ID: 338762bf-70e4-45dd-9772-5e95b0d56f27

Errors

[]

View original on GitHub ↗