roli-lpci/little-canary
Sacrificial LLM instances as behavioral probes for prompt injection detection
This project helps protect your AI applications, like chatbots or intelligent agents, from malicious instructions known as 'prompt injections.' It examines incoming user queries to see if they're trying to trick your AI into doing unintended things. The system takes in user input, analyzes it, and then tells your AI whether the input is safe, potentially harmful (with a warning), or should be blocked entirely, allowing you to build more secure AI experiences.
Available on PyPI.
Use this if you run an AI application or agent and need a lightweight, pre-check system to detect prompt injection attempts before they reach your main AI model.
Not ideal if you require formal security guarantees, audited benchmark comparability, or cannot accept that inputs will pass through unscreened if the security system is temporarily unavailable.
Stars
7
Forks
—
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 09, 2026
Commits (30d)
0
Dependencies
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/roli-lpci/little-canary"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Nebulock-Inc/agentic-threat-hunting-framework
ATHF is a framework for agentic threat hunting - building systems that can remember, learn, and...
AgentSeal/agentseal
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor...
cosai-oasis/secure-ai-tooling
The CoSAI Risk Map is a framework for identifying, analyzing, and mitigating security risks in...
HeadyZhang/agent-audit
Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis....
LucidAkshay/kavach
Tactical AI Workspace Monitor & EDR