hermes-labs-ai / little-canaryView on GitHub
Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.
27Aug 24, 2026Updated this week

Alternatives and similar repositories for little-canary

Users that are interested in little-canary are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?