Back to all repositories
HE
little-canary
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.
29stars4forks0watchers/subscribers1issues
agent-securityai-agentsai-safetycanaryclaude-code-plugindefense-in-depthdetectiondeveloper-toolsgemini-cli-extensionhermes-labsinput-validationjailbreak-detectionllmllm-securitypreflightprompt-injectionprompt-injection-detectionpython
- Language
- Python
- License
- Apache License 2.0
- Size
- 617 KB
- Created
- Feb 23, 2026
- Last Updated
- Sep 12, 2026
- Last Pushed
- Sep 12, 2026
Available Plugins
Loading plugins...
Evaluate before installing
- Review the source repository, recent maintenance, and license on GitHub.
- Read the marketplace manifest and plugin source files before running commands.
- Start with the smallest required permission set and validate behavior in a safe environment.