hermes-labs-ai/little-canary
v0.3.8Apache-2.0
Blocks a Claude Code turn when a local Little Canary server rejects the submitted prompt.
What this package declares
The file a client reads when it loads this plugin, exactly as this revision carries it.
plugin.json
{
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
"name": "little-canary",
"version": "0.3.8",
"description": "Blocks a Claude Code turn when a local Little Canary server rejects the submitted prompt.",
"author": {
"name": "Hermes Labs",
"email": "roli@hermes-labs.ai"
},
"homepage": "https://littlecanary.ai",
"repository": "https://github.com/hermes-labs-ai/little-canary",
"license": "Apache-2.0",
"keywords": ["prompt-injection", "llm-security", "agent-security", "canary", "hooks"]
}
This package publishes a manifest and nothing else
At this revision it ships no README, no skills, no MCP servers and no data for another client. Only plugin.json was indexed.