little-canary

SkillGitHubActivePython

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.

Description provenance: Original source

Open canonical source

Measured: Oct 24, 2026 · 43 observations

Domains & Uses

Domains: Agents, skills and MCP
Uses: Agent skills

Installation

/plugin marketplace add hermes-labs-ai/little-canary

Check at the source

Compatibility and prerequisites must be checked in the official documentation.

https://github.com/hermes-labs-ai/little-canary

Classifications

Nature: Tool

Measurement history

Comparable readings are grouped by signal and unit.

Stars

40stars · Oct 24, 2026

+12 (+42.9 %)since Sep 11, 2026

Exact values · 43 readings

Measured	stars	Change
Oct 24, 2026	40	0
Oct 23, 2026	40	+1
Oct 22, 2026	39	0
Oct 21, 2026	39	0
Oct 20, 2026	39	0
Oct 19, 2026	39	0
Oct 18, 2026	39	0
Oct 17, 2026	39	0
Oct 16, 2026	39	0
Oct 15, 2026	39	0
Oct 14, 2026	39	0
Oct 13, 2026	39	0
Oct 12, 2026	39	0
Oct 11, 2026	39	0
Oct 10, 2026	39	0
Oct 9, 2026	39	0
Oct 8, 2026	39	0
Oct 7, 2026	39	+1
Oct 6, 2026	38	0
Oct 5, 2026	38	0
Oct 4, 2026	38	0
Oct 3, 2026	38	0
Oct 2, 2026	38	0
Oct 1, 2026	38	0
Sep 30, 2026	38	+2
Sep 29, 2026	36	0
Sep 28, 2026	36	0
Sep 27, 2026	36	+2
Sep 26, 2026	34	+1
Sep 25, 2026	33	+1
Sep 24, 2026	32	0
Sep 23, 2026	32	0
Sep 22, 2026	32	+2
Sep 20, 2026	30	0
Sep 19, 2026	30	0
Sep 18, 2026	30	0
Sep 17, 2026	30	0
Sep 16, 2026	30	0
Sep 15, 2026	30	0
Sep 14, 2026	30	+1
Sep 13, 2026	29	+1
Sep 12, 2026	28	0
Sep 11, 2026	28	·