Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
1 result with any of your words
Clear search and filters
-
little-canary
SkillsDetects 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.
git clone https://github.com/hermes-labs-ai/little-canary.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.