Skip to main content
Back to all repositories

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

  1. Review the source repository, recent maintenance, and license on GitHub.
  2. Read the marketplace manifest and plugin source files before running commands.
  3. Start with the smallest required permission set and validate behavior in a safe environment.