[Bug] Custom validator triggers false positive spam detection

Status Open
Reported on v2.1.252
Maintainer reply None cached
Activity 0 comments · opened Sep 2, 2026

Bug Description
I was testing a custom anti-spam form validator and while Fable 5.1 was trying to trigger the validation, The model decided I was a bad actor. :-(
Response = "Fable 5's safeguards flagged this message. Our intentionally broad safeguards allow us to deliver more capabilities faster, but can sometimes flag legitimate coding, cybersecurity, and biology tasks. Switched to Opus 4.8. Send feedback with /feedback or learn more"

Details: [cyber]"
Environment Info

  • Platform: darwin
  • Terminal: iTerm.app
  • Version: 2.1.252
  • Feedback ID: 3ba27065-4d21-4a5d-9c95-9532c8ff546b

Errors

[]

View original on GitHub ↗