[Bug] False positive security detection when using Qwen model reasoning output
Status Open
Reported on v2.1.270
Maintainer reply None cached
Activity 0 comments · opened Sep 22, 2026
Bug Description
I was sending raw qwen 3 flash next reasoning and it took it as a reasoning extraction attack for some reason, and in my omarchy i have this weird shift stuck error as you will see at the end of that message, if this isnt a false positive, i mean, how can you guys make it SO easy that someone PASTING reasoning would cause it? OR its a really bad false positive.
Environment Info
- Platform: linux
- Terminal: xterm-256color
- Version: 2.1.270
- Feedback ID: f3223043-2c74-445f-9830-81185f8f1165
Errors
[]